# Scenema: long-form AI-animated explainers for creators and businesses > Scenema turns an idea, a script, or the material you already have (PDFs, slide decks, documents, spreadsheets, images, a reference video) into a finished, narrated, animated explainer video. It writes the script, records studio quality narration in more than 500 voices and 78 languages, designs a consistent cast of characters, places and props, plans every shot around the narration, generates the images and the animation in the style you choose, and exports an MP4. A project can hold as many chapters as it needs, and each chapter can run from 15 seconds to 30 minutes, so one project can be a two minute product demo, a thirty minute lesson, or a whole course or YouTube series. This page is the complete, plain description of Scenema for people and for AI assistants. It covers what Scenema makes, how the process works step by step, who it is for, every animation style, every narration voice, every language, the inputs it accepts, the exports it produces, the plans, and the ways to use it from other tools. Links point to live pages on scenema.ai. Where a feature is limited to paid plans or not available yet, this page says so. ## Contents 1. What Scenema is 2. Watch videos made in Scenema 3. How Scenema works, step by step 4. Why Scenema's animation holds together at length 5. Narration and audio 6. Your material as the source: file uploads 7. References: videos, images and music 8. Styles, and creating your own 9. Characters, places, props, logos and brand kit 10. Voice cloning for your story and your brand 11. Chapters, length, series and formats 12. Guided and agentic production 13. Editing after the first pass 14. Export, sharing and captions 15. Use cases for creators 16. Use cases for businesses and teams 17. Plans and credits 18. Using Scenema from other tools: MCP and API 19. What Scenema does not do today 20. Frequently asked questions 21. Every language 22. Every style 23. Every voice 24. Key pages ## 1. What Scenema is Scenema is a web app at [scenema.ai](https://scenema.ai) that makes long-form AI-animated explainer videos. You describe what you want to explain, or hand over a script or a stack of documents, and a production assistant called the Director interviews you about the audience, the goal, the length, the tone and the look. From there Scenema produces the whole video: the script, the narration, the storyboard, the recurring characters and places, a shot by shot plan timed to the narration, an image for every shot, the animation of each shot, and the final export. The word that matters most is long-form. Most AI video tools generate a single clip of a few seconds from a single prompt. Scenema plans and animates dozens or hundreds of shots and assembles them into one video, and it keeps the style, the characters, the locations and the props the same in every shot, from the first second to the last, at any length. That is what makes it possible to publish an eight minute YouTube explainer, a twenty minute training module, or a ten part course from one project. Scenema is built for two groups that need the same thing. Creators, such as YouTube educators, faceless channels, course creators and teachers, need long videos that look consistent and sound good, made fast enough to publish on a schedule. Businesses and teams, such as SaaS companies, training and HR teams, healthcare providers, agencies and marketers, need explainers, product demos, onboarding and training videos that stay on brand, show the real product and logo, and can be updated without a studio. You do not need animation skills, editing skills or a microphone. You also do not pick AI models: Scenema chooses the best model for your style and for each task, and you choose the quality and the resolution. ## 2. Watch videos made in Scenema These videos were made by Scenema users and are featured in the Made in Scenema section of the homepage. - **Doodle animation (Crude Doodle style):** *Every Service Is a Chemistry Lesson.* A nail technician explains the chemistry behind her work: mixtures, solutions and suspensions, and the pH scale. 1 minute 16 seconds. Video: https://cdn.scenema.ai/public/content/community/doodle-chemistry.mp4 . Poster: https://cdn.scenema.ai/public/content/community/doodle-chemistry-poster.webp - **3D cartoon (Glossy Preschool 3D style):** *Count to 10 with Little Monkey.* A preschool counting video from one to ten. 1 minute 37 seconds. Video: https://cdn.scenema.ai/public/content/community/little-monkey.mp4 . Poster: https://cdn.scenema.ai/public/content/community/little-monkey-poster.webp - **Paper collage (Paper Cutout Collage style):** *El Niño de la Tienda de Abarrotes.* A story told in Spanish in torn paper collage, chapter 1. 1 minute 6 seconds. Video: https://cdn.scenema.ai/public/content/community/nino-tienda-ch1.mp4 . Poster: https://cdn.scenema.ai/public/content/community/nino-tienda-ch1-poster.webp - **3D diorama (Warm Museum Diorama 3D style):** *Don't Leave That Money Behind.* A personal finance explainer, chapter 3. 29 seconds. Video: https://cdn.scenema.ai/public/content/community/money-behind-ch3.mp4 . Poster: https://cdn.scenema.ai/public/content/community/money-behind-ch3-poster.webp Every style in section 22 also links to its own page, with sample scenes generated in that style. ## 3. How Scenema works, step by step A Scenema video moves through a fixed set of stages. In guided mode you review and approve each one. In agentic mode the Director runs all of them for you after the interview (see section 12). ### 3.1 The interview with the Director You start on the homepage or the dashboard by typing what the video is about, optionally attaching files, and choosing a style, a length and a frame (landscape 16:9 or vertical 9:16). The Director then asks the questions a producer would ask: who the audience is, what they should know or do at the end, how long the video should be, whether it is one video or several parts, the tone, any facts that must be exact, the call to action, which source material to use, whether there is a video yours should feel like, and the narrator you want (gender, accent and delivery). On paid plans it also asks about quality. You answer in plain language in the chat. ### 3.2 The script The Director writes the script from what you told it and from your files, or uses your own script word for word if you paste one in. Scripts are written to be spoken: clear, conversational, and paced for listening. You can ask for changes in the chat ("make the opening a question", "keep it under 80 words", "make it funnier") and the script is rewritten. ### 3.3 The narration Scenema records the narration in the voice you picked, in one continuous pass, so the delivery, tone and energy stay the same from start to finish. You can listen, ask for a different voice or delivery, or upload your own recording instead (paid plans). Section 5 covers the audio in detail. ### 3.4 The look and the storyboard The style you chose sets the look and the motion language. The Director then writes a storyboard: the palette, the places, and the recurring characters and props, with what each shot shows and how things change from shot to shot. Each recurring element gets a written brief and a reference image generated in your style, and that reference is attached to every shot the element appears in. ### 3.5 Shot design Scenema plans the video shot by shot, timed to the narration. Each shot is between 5 and 15 seconds and illustrates the words spoken during it, so the picture always shows what is being said. For each shot it decides whether to cut or to continue in one take, writes the image prompt for every key moment (the keyframes) and the motion prompt for the animation, and plans the transitions so that one shot flows into the next. ### 3.6 Images and animation Scenema generates the keyframe images for every shot with the right references attached, and you can review them in the studio canvas. Once you approve, each shot is animated with the video model that suits the style and the motion best. Animation is optional: a shot can also stay a still image with a gentle pan and zoom. ### 3.7 Export The finished chapters are assembled with the narration into an MP4. You can export the whole project or chosen chapters, add burned in captions in one of nine caption styles, and share a public watch page. Section 14 covers export. ## 4. Why Scenema's animation holds together at length Making a single good AI clip is easy. Making a ten minute video where the same character looks the same in shot 3 and shot 140, where the kitchen in act one is the same kitchen in act three, and where every picture matches what the narrator is saying at that moment, is hard. Scenema is designed around that problem. - **Consistent characters, locations and props.** Every recurring element is stored with its own reference image. Every shot that includes it is generated with that reference attached, so faces, outfits, products, mascots and places stay the same across the whole video and across chapters. - **Consistent style.** The chosen style is a complete look and motion language, and it is applied to every shot. The look holds from the first shot to the last. - **Shots planned around the narration.** The narration is recorded first and every shot is cut to the exact words it illustrates. Key words land on the picture that shows them. - **Transitions and carry over.** Shots are designed in order, with what ends one shot carried into the start of the next, so the video reads as one continuous piece. - **Quality checks before you see it.** Scenema reviews its own shot prompts and the generated images against the style rules and the references, and fixes what it finds, so fewer problems reach you. - **The right model for each job.** Scenema runs a set of current image and video models and picks the best one for the style and each shot. Details are on the [AI models page](https://scenema.ai/ai-models). ## 5. Narration and audio Narration carries an explainer, so Scenema treats it as a first class part of the video. - **More than 500 voices.** The voice library has 501 narration voices with distinct ages, accents and personalities: documentary narrators, warm teachers, energetic presenters, calm advisors, storytellers, podcasters and commercial voices. Every voice has a public sample (section 23) and you can browse and search them on the [voices page](https://scenema.ai/voices). - **78 languages.** The library covers 78 languages, from English, Spanish, Mandarin, Hindi, Arabic, French, Portuguese and Russian to Amharic, Swahili, Javanese, Cebuano, Maithili and Luxembourgish (full list in section 21). Major languages have several regional accents. English alone has 110 voices across American, British, Indian, Australian, Canadian, Irish, South African and New Zealand English, and Spanish has Latin American and European Spanish. - **Expressive delivery.** The narration follows the meaning of the script: it slows down for a serious point, lifts for a reveal, and can laugh, sigh, gasp, whisper, or pause on cue. A chapter's narration style sets the overall delivery in plain words, for example "a calm, warm British documentary narrator" or "an upbeat children's science presenter". - **Clean, consistent sound.** Each chapter is read in one voice in one continuous pass, so there are no jumps in tone, level or energy between sentences, and the same voice reads every chapter. - **Your brand name said right.** Scenema handles brand and product pronunciation, so the narration says your name the way you say it while captions and on-screen text keep the correct spelling. - **Bring your own narration.** On paid plans you can upload your own recording (MP3, WAV, OGG, AAC, M4A or FLAC) and Scenema animates the video to it. - **Music driven explainers.** A song or an instrumental can drive a chapter instead of narration. Scenema maps its tempo, beats, sections and lyrics and cuts every shot on the beat, which suits music videos, lyric explainers, songs for children and rhythmic product montages. - **Audio only.** Scenema Audio, the speech engine behind the narration, is also available on its own for voiceovers, narration and text to speech from a script or a document. See [Scenema Audio](https://scenema.ai/audio). ## 6. Your material as the source: file uploads Most explainers start from material that already exists. Scenema works directly from it. - **Accepted files.** PDF, Word (DOC, DOCX), PowerPoint (PPT, PPTX), Excel (XLS, XLSX), OpenDocument text and slides (ODT, ODP), RTF, EPUB, CSV, TSV, TXT, Markdown and JSON, plus images, audio and video. Each file can be up to 20 MB, and one analysis can take up to 50 files. - **How files are used.** Your files are attached to the model as they are, so it reads the actual pages, slides, tables and images. Office documents are converted to PDF so every page keeps its layout. Scenema writes a source analysis of your material (the angle, the facts that must stay exact, and how each image should be used) and the script, the storyboard and the shot design all work from it. - **Exact facts stay exact.** Numbers, names, quotes and steps from your material are kept as written. A page, a chart or a table from a document can be shown in the video exactly as it appears. - **Typical sources.** A research paper turned into a YouTube explainer, a slide deck turned into a training module, a product spec turned into a demo, a policy document turned into compliance training, a book chapter turned into a lesson, or a spreadsheet turned into a data story. ## 7. References: videos, images and music ### 7.1 A video as a reference If there is a video yours should feel like, give it to the Director: paste up to three YouTube links in the chat or upload a video file. Scenema studies its pacing, cut rhythm, opening, transitions, on-screen text and look, and the script, storyboard and shot design borrow its craft. Your video keeps your own content. If you have no reference, Scenema can find a fitting reference video on YouTube for you. ### 7.2 Images as references and inspiration You can upload images and say how each one should be used: - **Shown exactly:** a logo, a product photo, a screenshot or a document page appears as it is. - **As a guide:** Scenema creates a character, place or prop in your chosen style based on the image, for example your real product redrawn in whiteboard style, or your founder as a 3D character. - **As inspiration only:** the image informs the mood or the look without becoming a fixed element. ### 7.3 Music driven explainers Upload a song or an instrumental and it becomes the soundtrack the chapter is built on. Scenema maps the tempo, the beats, the sections and the timed lyrics, then plans the shots so each one lands on the beat and illustrates the lyric or the idea of that moment. This suits music videos, lyric explainers, educational songs for children, and rhythmic brand and product montages. ## 8. Styles, and creating your own Scenema has 78 ready made styles in 15 families, each a complete look and motion language that is applied to every shot. They range from whiteboard and doodle animation, flat 2D explainer characters, anime and picture book watercolour, to motion graphics, data charts, kinetic typography and app walkthroughs, to paper collage, woodblock prints and ink wash, to 3D characters, isometric dioramas, claymation, product renders, technical cutaways and cinematic photoreal. The full list, with a link, a thumbnail and a description for every style, is in section 22, and you can browse them on the [styles page](https://scenema.ai/styles). **Custom styles.** On paid plans you can create your own style in the Styles Studio from a reference image, a short video clip (up to a 30 second window), a text description, or media plus a short note. Scenema analyses the reference and writes a production style: a name, a description, a category, tags, the style instructions every shot follows, and a colour palette. Custom styles are private to your workspace and work exactly like the built in ones. This is how a brand gets its own house look, or a channel gets a signature style no one else has. ## 9. Characters, places, props, logos and brand kit Every recurring element of a video is a named entity with a reference image: the presenter, a mascot, the customer, the product, the office, the factory floor, the app screen, the logo. Entities are what keep a long video consistent, and they are also how a brand shows up correctly inside the story. - **Logos and products shown exactly.** Upload your logo, product photos or app screenshots and mark them to be shown exactly, and they appear as they are in the shots that need them. - **Your real people and places in your style.** Upload a photo as a guide and Scenema creates the person, the place or the product in your chosen style, then keeps it the same in every shot. - **Brand colours and look.** A custom style built from your brand imagery carries your palette and visual language into every shot. ### 9.1 Brand kit The brand kit keeps every video a workspace exports visually on brand. A workspace sets up its brand once, and the kit is applied to its videos: - **Logo upload or wordmark.** Upload your logo, or set a text wordmark with your own font, weight and colour. - **Placement.** Choose the corner (top left, top right, bottom left or bottom right), the size, the margin and the opacity, so the mark sits where your brand guidelines want it. - **One kit for the whole team.** The kit belongs to the workspace, so every video anyone on the team makes carries the same branding. Together with logos shown exactly inside the shots, a custom house style and a cloned brand voice, the brand kit means a company's hundredth video looks and sounds like its first. ## 10. Voice cloning for your story and your brand A voice is part of how people recognise you. Voice cloning lets your videos be narrated in your own voice, or in the voice of the person who should be telling the story. - **Tell your story in your own voice.** A creator can narrate every episode of a channel in their own voice without recording each one. A teacher can have every lesson sound like them. A founder can explain the product in the voice customers already know from calls and talks. - **Brand consistency.** A company can give its brand one recognisable voice and use it across product demos, onboarding, training, support videos and ads, so every video sounds like the same company, in every chapter and every project. - **How it works.** On the Voices page choose Create voice, upload an audio file or record in the browser (10 to 30 seconds of one person speaking clearly is ideal, and at least 3 seconds of clear speech is required), give the voice a name, gender and language, and confirm you have the speaker's consent. The cloned voice then appears next to the library voices and can narrate any project in your workspace. - **Many languages.** A cloned voice can narrate in 66 languages, so the same recognisable voice can carry a video into new markets. - **Consent.** Cloning always requires confirming that you have the speaker's permission. ## 11. Chapters, length, series and formats - **Chapters.** A project holds as many chapters as it needs. Each chapter runs from 15 seconds to 30 minutes. One project can be a single video, a multi part series, a course with one chapter per lesson, or a long documentary in parts. - **Carry over between chapters.** Each new chapter carries over the voice, language, style and cast of the one before it, so a series stays consistent. - **Length options.** When you start, you can pick Auto, 15 seconds, 30 seconds, 60 seconds, 2, 5, 10 or 15 minutes, or ask the Director for any length up to 30 minutes per chapter. - **Frames.** Landscape 16:9 for YouTube, websites and presentations, and vertical 9:16 for Shorts, Reels and TikTok. Square 1:1 is available through MCP. You can switch the frame at any stage: everything made in the old frame is kept, and switching back reuses it. - **Resolution.** 480p, 720p and 1080p, depending on your plan (section 17). ## 12. Guided and agentic production - **Guided (the default).** You review and approve each step: the script, the narration, the storyboard, the keyframes, and the animation. You can change anything before moving on. - **Agentic.** After the interview, the Director runs every step through to the export on its own and keeps you posted with progress updates in the chat, plus emails along the way and at the end. Failed steps are retried automatically. If you write in the chat, the run pauses so the Director can answer, and you can switch between guided and agentic at any time. ## 13. Editing after the first pass Everything stays editable. You can rewrite part of the script, change the voice or the delivery, redesign a shot, regenerate a single keyframe or a single animation, swap a character's reference, change the style of a chapter, or switch the frame, and only the affected parts are redone. You can make these changes by asking the Director in the chat or directly in the studio's shot editor. ## 14. Export, sharing and captions - **MP4 export** of the whole project or chosen chapters. - **Captions** burned into the video in nine styles (basic, cc, cue, pill, pop, marker, typewriter, neon and spotlight), four sizes, four positions, five fonts and your own colours. Captions are off unless you turn them on. - **Downloads ZIP** on Creator and Pro, with an SRT subtitle file and every shot as a separate clip, ready for DaVinci Resolve, Premiere or any editor. - **A public watch page** for every export at scenema.ai/v/ followed by the export id, ready to share. - **Watermark.** Free plan exports carry a Scenema watermark. Paid plan exports do not. ## 15. Use cases for creators - **YouTube explainers and video essays.** Science, history, finance, technology, psychology and culture channels publish long, consistent videos on a schedule, including videos long enough for mid-roll ads. - **Faceless channels.** A narrator voice and an animated style give a channel a recognisable identity with no camera and no microphone. - **Series.** One project, one chapter per episode, the same narrator, style and recurring characters in every episode. - **Courses and lessons.** Teachers and course creators turn lesson notes, slides or a textbook chapter into narrated animated lessons, one chapter per lesson. - **Children's content.** Counting, letters, stories and science for young learners in picture book, preschool 3D, claymation or rounded mascot styles. - **History and documentaries.** Maps, engravings, manuscripts, woodblock prints and cinematic 3D for long documentary storytelling. - **Shorts, Reels and TikTok.** Vertical 9:16 versions of explainers, or short pieces in their own right. - **Music videos and songs.** Musicians and children's channels turn a track into an animated video cut on the beat. - **Videos in many languages.** The same video narrated in 78 languages to reach new audiences. ## 16. Use cases for businesses and teams - **Product demos and feature launches.** SaaS and app companies show the real product, with screens shown exactly and the brand's logo, in app walkthrough, motion graphics or 3D styles. - **Employee training, onboarding and compliance.** HR and L&D teams turn policies and handbooks into clear, consistent training modules with do and do not examples. - **Customer education and support.** How to videos, setup guides and explainers that reduce support tickets. - **Healthcare and patient education.** Procedures, conditions and care instructions explained calmly in friendly or biomedical styles. - **Marketing and brand explainers.** Homepage explainers, campaign videos and social content that stay on brand. - **Sales enablement.** Pitch explainers and use case videos for each audience or market. - **Agencies.** Animated explainers for clients at a pace and price a studio cannot match, in the client's own style and voice. - **Engineering, manufacturing and energy.** How machines and systems work, with technical cutaways, blueprints and isometric diagrams. - **Finance and fintech.** Data stories, product flows and investor explainers in clean editorial or fintech styles. - **Internal communications.** Company updates, strategy explainers and change management videos in many languages. ## 17. Plans and credits Scenema has a free plan and three paid plans. Credits pay for generation and for chatting with the Director. Current prices and details are on the [pricing page](https://scenema.ai/pricing). | Plan | Price | Credits | Highlights | | :--- | :--- | :--- | :--- | | Free | $0 | 200 once at signup | Draft quality at 480p, watermarked exports, scripts up to 1,000 characters | | Starter | $9 a month | 1,000 a month | Up to 720p, voice cloning, your own narration, reference images | | Creator | $58 a month, or $29 a month billed yearly | 3,000 a month | Up to 1080p, brand kit, downloads ZIP, 5 team members | | Pro | $250 a month, or $125 a month billed yearly | 15,000 a month | Up to 1080p, brand kit, unlimited reference images, unlimited team members | Paid plans include the Voices and Styles studios, custom styles, and credit packs. No credit card is needed to start on the free plan. ## 18. Using Scenema from other tools: MCP and API - **MCP server.** Scenema runs a Model Context Protocol server at https://mcp.scenema.ai/mcp, so assistants such as Claude, ChatGPT, Cursor, Windsurf and Claude Code can create and produce Scenema videos for you. Sign in with OAuth from Claude or ChatGPT connectors, or use a personal API key. MCP works on every plan. Docs: [MCP](https://scenema.ai/docs/api/mcp). - **REST API.** The same production steps are available over HTTPS at https://scenema.ai/api/service with an API key. Docs: [API](https://scenema.ai/docs/api). ## 19. What Scenema does not do today Scenema does not make lip synced or dialogue based films. Its videos are narrated or music driven explainers, so on-screen characters do not speak lines to each other or to the camera. ## 20. Frequently asked questions **How long can a Scenema video be?** Each chapter can run up to 30 minutes and a project can have as many chapters as it needs. **Do the characters stay the same throughout the video?** Yes. Every recurring character, place and prop has a reference image that is attached to every shot it appears in. **Can I use my own script?** Yes. Paste it in and Scenema keeps it word for word. **Can I make a video from a PDF or a slide deck?** Yes. Upload it and Scenema writes the script, the narration and the shots from it. **Can the video show my real logo and product?** Yes. Upload them and mark them to be shown exactly, and set up a brand kit to put your logo or wordmark on every video. **Can I use my own voice?** Yes. Clone your voice, or upload your own recording as the narration. **Which languages are supported?** 78 languages for narration, listed in section 21. **Do I need to choose an AI model?** No. Scenema picks the best model for your style and each shot. **Can I make vertical videos?** Yes, 9:16 for Shorts, Reels and TikTok. **Is there a free plan?** Yes, with 200 credits at signup and no credit card. **Can Claude or ChatGPT make Scenema videos for me?** Yes, through the Scenema MCP server. **Can I edit a single shot?** Yes. Any shot, keyframe or animation can be changed or regenerated on its own. ## 21. Every language Scenema narrates in 78 languages with 501 library voices. Each entry gives the language, its own name for itself, the number of voices, and the regional accents available. The [voices page](https://scenema.ai/voices) lets you filter by language and accent. - **Afrikaans**: 2 voices. - **Albanian** (Shqip): 2 voices. - **Amharic** (አማርኛ): 4 voices. - **Arabic** (العربية): 20 voices. Accents: ar-001 (14), ar-EG (6). - **Armenian** (Հայերեն): 2 voices. - **Assamese** (অসমীয়া): 2 voices. - **Azerbaijani** (Azərbaycanca): 2 voices. - **Basque** (Euskara): 2 voices. - **Belarusian** (Беларуская): 2 voices. - **Bengali** (বাংলা): 4 voices. - **Bulgarian** (Български): 2 voices. - **Burmese** (မြန်မာ): 2 voices. - **Cantonese** (粵語): 4 voices. - **Catalan** (Català): 2 voices. - **Cebuano**: 2 voices. - **Chinese (Mandarin)** (中文): 25 voices. - **Croatian** (Hrvatski): 2 voices. - **Czech** (Čeština): 2 voices. - **Danish** (Dansk): 2 voices. - **Dutch** (Nederlands): 4 voices. Accents: nl-NL (4). - **English**: 110 voices. Accents: en-US (38), en-GB (20), en-IN (12), en-AU (10), en-CA (10), en-IE (8), en-ZA (8), en-NZ (4). - **Estonian** (Eesti): 2 voices. - **Filipino**: 4 voices. - **Finnish** (Suomi): 2 voices. - **French** (Français): 20 voices. Accents: fr-FR (12), fr-CA (8). - **Galician** (Galego): 2 voices. - **Georgian** (ქართული): 2 voices. - **German** (Deutsch): 17 voices. Accents: de-DE (16). - **Greek** (Ελληνικά): 2 voices. Accents: el-GR (2). - **Gujarati** (ગુજરાતી): 2 voices. - **Haitian Creole** (Kreyòl ayisyen): 2 voices. - **Hebrew** (עברית): 4 voices. - **Hindi** (हिन्दी): 24 voices. Accents: hi-IN (23). - **Hungarian** (Magyar): 2 voices. - **Icelandic** (Íslenska): 2 voices. - **Indonesian** (Bahasa Indonesia): 4 voices. - **Italian** (Italiano): 12 voices. Accents: it-IT (8). - **Japanese** (日本語): 16 voices. Accents: ja-JP (16). - **Javanese** (Jawa): 2 voices. - **Kannada** (ಕನ್ನಡ): 2 voices. - **Kazakh** (Қазақша): 2 voices. - **Korean** (한국어): 16 voices. Accents: ko-KR (16). - **Lao** (ລາວ): 2 voices. - **Latvian** (Latviešu): 2 voices. - **Lithuanian** (Lietuvių): 2 voices. - **Luxembourgish** (Lëtzebuergesch): 2 voices. - **Macedonian** (Македонски): 2 voices. - **Maithili** (मैथिली): 2 voices. - **Malay** (Bahasa Melayu): 2 voices. - **Malayalam** (മലയാളം): 2 voices. - **Marathi** (मराठी): 4 voices. - **Mongolian** (Монгол): 2 voices. - **Nepali** (नेपाली): 2 voices. - **Norwegian Bokmål** (Norsk bokmål): 2 voices. - **Odia** (ଓଡ଼ିଆ): 2 voices. - **Pashto** (پښتو): 2 voices. - **Persian** (فارسی): 4 voices. - **Polish** (Polski): 4 voices. Accents: pl-PL (3). - **Portuguese** (Português): 20 voices. Accents: pt-BR (14), pt-PT (6). - **Punjabi** (ਪੰਜਾਬੀ): 2 voices. - **Romanian** (Română): 2 voices. - **Russian** (Русский): 21 voices. - **Serbian** (Српски): 2 voices. - **Sindhi** (سنڌي): 2 voices. - **Sinhala** (සිංහල): 2 voices. - **Slovak** (Slovenčina): 2 voices. - **Slovenian** (Slovenščina): 2 voices. - **Spanish** (Español): 34 voices. Accents: es-419 (24), es-ES (10). - **Swahili** (Kiswahili): 4 voices. Accents: sw-KE (2). - **Swedish** (Svenska): 2 voices. - **Tamil** (தமிழ்): 4 voices. Accents: ta-IN (2). - **Telugu** (తెలుగు): 4 voices. Accents: te-IN (3). - **Thai** (ไทย): 4 voices. - **Turkish** (Türkçe): 4 voices. - **Ukrainian** (Українська): 2 voices. - **Urdu** (اردو): 4 voices. - **Uzbek** (Oʻzbekcha): 2 voices. - **Vietnamese** (Tiếng Việt): 4 voices. Accents: vi-VN (4). ## 22. Every style Scenema has 78 ready made styles in 15 families. Each style links to its page on scenema.ai, which shows sample scenes made in that style, its palette and the videos it suits. The thumbnail link is a sample image generated in the style. Browse them all on the [styles page](https://scenema.ai/styles). ### 2D animation (21 styles) Flat characters, bold shapes and bright color: the look of most explainer videos on the web. From corporate training to anime, picture books and comics, there is a look for every story. Family page: https://scenema.ai/styles/2d-animated-explainer - **[Flat Cartoon Infographic](https://scenema.ai/styles/2d-animated-explainer/flat-cartoon-infographic)**: Bright flat cartoon characters with thick outlines and bold infographic layouts, the popular What If YouTube look. Thumbnail: https://cdn.scenema.ai/public/content/styles/flat-cartoon-infographic/scenes/your-body-without-water.webp - **[Chibi History Map](https://scenema.ai/styles/2d-animated-explainer/chibi-history-map)**: Big headed cartoon generals, kings and soldiers marching across painted parchment maps. Thumbnail: https://cdn.scenema.ai/public/content/styles/chibi-history-map/scenes/hannibals-march.webp - **[Crude Doodle](https://scenema.ai/styles/2d-animated-explainer/crude-doodle)**: Deliberately simple, wobbly marker stick figures with big expressions and scribbled labels, funny and relatable. Thumbnail: https://cdn.scenema.ai/public/content/styles/crude-doodle/scenes/why-you-procrastinate.webp - **[Flat Corporate Training](https://scenema.ai/styles/2d-animated-explainer/corporate-training)**: Clean, professional flat vector characters in real workplaces, with do and do not examples and clear steps. Thumbnail: https://cdn.scenema.ai/public/content/styles/corporate-training/scenes/use-a-fire-extinguisher.webp - **[Glossy Preschool 3D](https://scenema.ai/styles/2d-animated-explainer/glossy-preschool-3d)**: Bright, glossy 3D for little learners: big shiny eyes, candy colours, sunny hills and toy towns. Thumbnail: https://cdn.scenema.ai/public/content/styles/glossy-preschool-3d/scenes/shapes-all-around.webp - **[Halftone Comic](https://scenema.ai/styles/2d-animated-explainer/halftone-comic)**: Bold inks and Ben Day dots in red, blue and yellow, with dynamic panels, speed lines and caption boxes. Thumbnail: https://cdn.scenema.ai/public/content/styles/halftone-comic/scenes/how-vaccines-work.webp - **[Anime Cel](https://scenema.ai/styles/2d-animated-explainer/anime-cel)**: Hand drawn anime with clean line art, cel shading, expressive characters and painted summer skies. Thumbnail: https://cdn.scenema.ai/public/content/styles/anime-cel/scenes/the-water-cycle.webp - **[Cosmic Flat Science](https://scenema.ai/styles/2d-animated-explainer/cosmic-flat-science)**: Bold flat shapes, soft glows and tiny characters explain space, biology and the big questions with a grand sense of scale. Thumbnail: https://cdn.scenema.ai/public/content/styles/cosmic-flat-science/scenes/inside-the-sun.webp - **[Graphic Novel Noir](https://scenema.ai/styles/2d-animated-explainer/graphic-novel-noir)**: High contrast ink noir with heavy shadows, rain and venetian blinds, and a single blood red accent. Thumbnail: https://cdn.scenema.ai/public/content/styles/graphic-novel-noir/scenes/reading-the-scene.webp - **[Lavender Glass Tech](https://scenema.ai/styles/2d-animated-explainer/lavender-glass-tech)**: Flat vector characters with floating frosted glass UI in one lavender to indigo palette. Thumbnail: https://cdn.scenema.ai/public/content/styles/lavender-glass-tech/scenes/book-a-trip-in-three-taps.webp - **[Lime Line Editorial](https://scenema.ai/styles/2d-animated-explainer/lime-line-editorial)**: Minimal editorial line art with one electric lime spot color on clean light gray. Thumbnail: https://cdn.scenema.ai/public/content/styles/lime-line-editorial/scenes/dress-for-the-site.webp - **[Mid-Century Cartoon](https://scenema.ai/styles/2d-animated-explainer/mid-century-cartoon)**: 1950s limited animation with angular characters, mustard, teal and coral, boomerangs and starbursts. Thumbnail: https://cdn.scenema.ai/public/content/styles/mid-century-cartoon/scenes/watch-your-savings-grow.webp - **[Painterly Countryside Anime](https://scenema.ai/styles/2d-animated-explainer/painterly-countryside-anime)**: Warm hand painted countryside anime: lush meadows, big clouds, cosy villages, gentle characters and little forest sprites. Thumbnail: https://cdn.scenema.ai/public/content/styles/painterly-countryside-anime/scenes/the-wood-wide-web.webp - **[Painterly Gouache](https://scenema.ai/styles/2d-animated-explainer/painterly-gouache)**: Textured gouache editorial illustration: elongated, expressive characters, lush plants and sunflower yellow against midnight navy. Thumbnail: https://cdn.scenema.ai/public/content/styles/painterly-gouache/scenes/the-letter.webp - **[Pixel Art](https://scenema.ai/styles/2d-animated-explainer/pixel-art)**: Crisp 16 bit pixel art with chunky characters, retro palettes and side scrolling game worlds. Thumbnail: https://cdn.scenema.ai/public/content/styles/pixel-art/scenes/adding-a-block.webp - **[Risograph Editorial](https://scenema.ai/styles/2d-animated-explainer/risograph-editorial)**: Grainy screen print editorial vector: indigo silhouettes under saffron sun domes, with paper tooth and stipple. Thumbnail: https://cdn.scenema.ai/public/content/styles/risograph-editorial/scenes/how-malaria-spreads.webp - **[Rounded Mascot](https://scenema.ai/styles/2d-animated-explainer/rounded-mascot)**: Friendly, bouncy characters built from soft rounded shapes and cheerful flat colour, with an original fox mascot. Thumbnail: https://cdn.scenema.ai/public/content/styles/rounded-mascot/scenes/the-habit-loop.webp - **[Stipple Luxury](https://scenema.ai/styles/2d-animated-explainer/stipple-luxury)**: Luxury editorial vector with stippled light: elegant silhouettes, velvet, candlelight and gold on midnight navy. Thumbnail: https://cdn.scenema.ai/public/content/styles/stipple-luxury/scenes/signature-suite.webp - **[Twilight City Vector](https://scenema.ai/styles/2d-animated-explainer/twilight-city-vector)**: Flat vector streets and isometric city blocks at dusk, with lamp glow and friendly semi flat characters. Thumbnail: https://cdn.scenema.ai/public/content/styles/twilight-city-vector/scenes/find-a-spot-fast.webp - **[Vector Parallax](https://scenema.ai/styles/2d-animated-explainer/vector-parallax)**: Calm layered vector landscapes with a coral rim light: mountains, rivers and forests built for parallax. Thumbnail: https://cdn.scenema.ai/public/content/styles/vector-parallax/scenes/life-of-a-river.webp - **[Watercolour Picture Book](https://scenema.ai/styles/2d-animated-explainer/watercolour-picture-book)**: Soft hand painted watercolour like a beloved children's book, with sweet characters and gentle pastel colour. Thumbnail: https://cdn.scenema.ai/public/content/styles/watercolour-picture-book/scenes/butterfly-life-cycle.webp ### Motion graphics (11 styles) Charts, maps, interfaces and type that move with the narration. Use them for product walkthroughs, data stories and documentaries where the numbers carry the argument. Family page: https://scenema.ai/styles/motion-graphics - **[App Walkthrough](https://scenema.ai/styles/motion-graphics/app-walkthrough)**: Crisp product screens in clean device frames, with a guiding cursor, zoom callouts, highlight rings and step badges. Thumbnail: https://cdn.scenema.ai/public/content/styles/app-walkthrough/scenes/connect-your-bank.webp - **[Documentary Terrain Map](https://scenema.ai/styles/motion-graphics/documentary-terrain-map)**: Cinematic shaded relief maps on aged paper, with glowing amber routes, red pins and clean label tags. Thumbnail: https://cdn.scenema.ai/public/content/styles/documentary-terrain-map/scenes/strait-of-hormuz.webp - **[Editorial Data Charts](https://scenema.ai/styles/motion-graphics/editorial-data-charts)**: Bold, beautifully annotated newspaper style charts on newsprint, with one red highlight telling the story. Thumbnail: https://cdn.scenema.ai/public/content/styles/editorial-data-charts/scenes/first-mortgage-payment.webp - **[Brutalist](https://scenema.ai/styles/motion-graphics/brutalist)**: Raw brutalist graphic design: huge black grotesque type, hard grids, clashing acid colour blocks and halftone cutouts. Thumbnail: https://cdn.scenema.ai/public/content/styles/brutalist/scenes/anatomy-of-a-phishing-email.webp - **[Cobalt Fintech 2.5D](https://scenema.ai/styles/motion-graphics/cobalt-fintech-2-5d)**: Strict cobalt and white 2.5D vector with flat geometric hands, soft shadowed cards and a friendly capsule bot. Thumbnail: https://cdn.scenema.ai/public/content/styles/cobalt-fintech-2-5d/scenes/sending-money-abroad.webp - **[Dark Minimal Documentary](https://scenema.ai/styles/motion-graphics/dark-minimal-documentary)**: Near black frames with film grain, thin white line graphics, glowing timelines and a single amber accent. Thumbnail: https://cdn.scenema.ai/public/content/styles/dark-minimal-documentary/scenes/the-first-message.webp - **[Flat Vector Map](https://scenema.ai/styles/motion-graphics/flat-vector-map)**: Clean flat maps in off white and deep blue, with orange highlights, red data dots and dotted flight arcs. Thumbnail: https://cdn.scenema.ai/public/content/styles/flat-vector-map/scenes/where-australians-live.webp - **[Kinetic Typography](https://scenema.ai/styles/motion-graphics/kinetic-typography)**: The words are the visuals: huge bold type that slams, stacks and swaps in time with the narration, poster style. Thumbnail: https://cdn.scenema.ai/public/content/styles/kinetic-typography/scenes/how-to-give-feedback.webp - **[Math Visualization on Dark](https://scenema.ai/styles/motion-graphics/math-visualization-dark)**: Precise animated geometry, coordinate grids and typeset equations that transform smoothly on a deep night background. Thumbnail: https://cdn.scenema.ai/public/content/styles/math-visualization-dark/scenes/eigenvectors.webp - **[Midnight Fintech Geometric](https://scenema.ai/styles/motion-graphics/midnight-fintech-geometric)**: Flat violet and coral UI cards, faceted coins and neon mint circuit lines on midnight navy. Thumbnail: https://cdn.scenema.ai/public/content/styles/midnight-fintech-geometric/scenes/how-a-crypto-backed-loan-works.webp - **[Starship Console](https://scenema.ai/styles/motion-graphics/starship-console)**: A retro futuristic starship computer interface: rounded elbow bars, pill buttons and flat schematics on black. Thumbnail: https://cdn.scenema.ai/public/content/styles/starship-console/scenes/solar-system-survey.webp ### Whiteboard (8 styles) Start from an idea, a finished script or the material you already have, like a PDF, a slide deck or your notes. Scenema writes the script, draws every scene in a hand drawn style and narrates it, from a two minute explainer to a full course module. Family page: https://scenema.ai/styles/whiteboard-animation - **[One Line Drawing](https://scenema.ai/styles/whiteboard-animation/one-line-drawing)**: A single unbroken line draws every idea and flows into the next, with one warm accent on warm paper. Thumbnail: https://cdn.scenema.ai/public/content/styles/one-line-drawing/scenes/anatomy-of-a-bicycle.webp - **[Digital Ink on Black](https://scenema.ai/styles/whiteboard-animation/digital-ink-on-black)**: Equations, diagrams and handwriting write themselves on a pure black screen in clean, softly glowing coloured ink. Thumbnail: https://cdn.scenema.ai/public/content/styles/digital-ink-on-black/scenes/separable-differential-equation.webp - **[Ink and Hatch Whiteboard](https://scenema.ai/styles/whiteboard-animation/ink-and-hatch-whiteboard)**: A real hand draws bold marker cartoons with cross-hatching and a few mint, coral, green and marigold washes on a white board. Thumbnail: https://cdn.scenema.ai/public/content/styles/ink-and-hatch-whiteboard/scenes/compound-interest.webp - **[Sketchnote](https://scenema.ai/styles/whiteboard-animation/sketchnote)**: Visual notes on a dotted notebook page: fineliner lettering, doodles, arrows and two bright highlighters. Thumbnail: https://cdn.scenema.ai/public/content/styles/sketchnote/scenes/pomodoro-technique.webp - **[Chalkboard](https://scenema.ai/styles/whiteboard-animation/chalkboard)**: A real hand draws friendly diagrams, scenes and lettering in dusty chalk on a green black slate board. Thumbnail: https://cdn.scenema.ai/public/content/styles/chalkboard/scenes/plant-cell.webp - **[Ink Caricature Whiteboard](https://scenema.ai/styles/whiteboard-animation/ink-caricature-whiteboard)**: A real hand draws expressive ink caricatures on white, with soft teal and rose spot color. Thumbnail: https://cdn.scenema.ai/public/content/styles/ink-caricature-whiteboard/scenes/how-a-bill-becomes-law.webp - **[Pure Ink Whiteboard](https://scenema.ai/styles/whiteboard-animation/pure-ink-whiteboard)**: The classic whiteboard animation: a real hand draws bold black marker cartoons with hatching on a clean white board, no colour. Thumbnail: https://cdn.scenema.ai/public/content/styles/pure-ink-whiteboard/scenes/how-a-heat-pump-works.webp - **[Spot Color Caricature Whiteboard](https://scenema.ai/styles/whiteboard-animation/spot-color-caricature-whiteboard)**: Big headed comic caricatures and whimsical machines drawn live on white, lit up with cyan, magenta and lime. Thumbnail: https://cdn.scenema.ai/public/content/styles/spot-color-caricature-whiteboard/scenes/why-satellites-stay-up.webp ### Paper and fine art (7 styles) Styles borrowed from museum walls and craft tables: woodblock prints, ink wash, illuminated manuscripts, origami and shadow puppets. They suit history, culture and storytelling. Family page: https://scenema.ai/styles/paper-and-art-styles - **[Black-Figure Pottery](https://scenema.ai/styles/paper-and-art-styles/black-figure-pottery)**: Ancient Greek vase painting: black silhouette figures with incised detail on terracotta, framed by meander friezes. Thumbnail: https://cdn.scenema.ai/public/content/styles/black-figure-pottery/scenes/the-ancient-olympics.webp - **[Chinese Ink Wash](https://scenema.ai/styles/paper-and-art-styles/chinese-ink-wash)**: Traditional shuimo ink painting brought to life: flowing sumi brushstrokes, misty washes and rice paper, poetic and serene. Thumbnail: https://cdn.scenema.ai/public/content/styles/chinese-ink-wash/scenes/the-way-of-tea.webp - **[Illuminated Manuscript](https://scenema.ai/styles/paper-and-art-styles/illuminated-manuscript)**: Medieval manuscript painting in lapis, vermilion and gold leaf, with vine borders and gothic arches. Thumbnail: https://cdn.scenema.ai/public/content/styles/illuminated-manuscript/scenes/how-a-book-was-made.webp - **[Newsroom Paper Collage](https://scenema.ai/styles/paper-and-art-styles/newsroom-paper-collage)**: Halftone photo cutouts layered as a deep paper diorama on aged newsprint, with giant stat numbers and one hot accent. Thumbnail: https://cdn.scenema.ai/public/content/styles/newsroom-paper-collage/scenes/the-cost-of-a-basket.webp - **[Papercraft Origami](https://scenema.ai/styles/paper-and-art-styles/papercraft-origami)**: Pure white papercraft that folds and pops up into cities, venues and ideas, with gold foil on the one thing that matters. Thumbnail: https://cdn.scenema.ai/public/content/styles/papercraft-origami/scenes/festival-grounds.webp - **[Silhouette Shadow Puppet](https://scenema.ai/styles/paper-and-art-styles/silhouette-shadow-puppet)**: Lace fine black cut paper silhouettes in profile against glowing amber and rose skies, like a lantern lit puppet theatre. Thumbnail: https://cdn.scenema.ai/public/content/styles/silhouette-shadow-puppet/scenes/the-silk-road.webp - **[Ukiyo-e Woodblock](https://scenema.ai/styles/paper-and-art-styles/ukiyo-e-woodblock)**: Japanese woodblock prints with flowing key lines, Prussian blue waves, misty mountains and soft graded skies. Thumbnail: https://cdn.scenema.ai/public/content/styles/ukiyo-e-woodblock/scenes/the-tokaido-road.webp ### Isometric 3D (5 styles) Small worlds seen from above at a clean angle. Isometric dioramas show how a system fits together, from a factory floor to a city block. Family page: https://scenema.ai/styles/isometric-3d-animation - **[Azure Isometric 3D](https://scenema.ai/styles/isometric-3d-animation/azure-isometric-3d)**: Monochrome blue isometric 3D: satin platforms with glowing orange edges, extruded maps and charts for data and investor stories. Thumbnail: https://cdn.scenema.ai/public/content/styles/azure-isometric-3d/scenes/our-supply-chain.webp - **[Low Poly Isometric](https://scenema.ai/styles/isometric-3d-animation/low-poly-isometric)**: Monochrome low poly isometric 3D: grey clay dioramas, glowing white rings on the key object and sparing crimson warnings. Thumbnail: https://cdn.scenema.ai/public/content/styles/low-poly-isometric/scenes/end-to-end-encryption.webp - **[Nordic Diorama 3D](https://scenema.ai/styles/isometric-3d-animation/nordic-diorama-3d)**: High-key architectural miniature 3D: matte white buildings and mannequins, sponge green trees and glowing energy lines. Thumbnail: https://cdn.scenema.ai/public/content/styles/nordic-diorama-3d/scenes/sun-to-socket.webp - **[Pastel Stop Motion](https://scenema.ai/styles/isometric-3d-animation/pastel-stop-motion)**: Tactile pastel architecture in stop motion: arches, ramps and blocks stacked into playful buildings on dusty rose. Thumbnail: https://cdn.scenema.ai/public/content/styles/pastel-stop-motion/scenes/inside-the-residence.webp - **[Violet Clay Isometric](https://scenema.ai/styles/isometric-3d-animation/violet-clay-isometric)**: Soft clay isometric dioramas on deep violet: white platforms, phones and tiny worlds with lemon, mint and cyan accents. Thumbnail: https://cdn.scenema.ai/public/content/styles/violet-clay-isometric/scenes/how-your-store-runs.webp ### 3D product (4 styles) Studio lit products and brand worlds in polished 3D. Made for launches, ads and hero shots where the object is the star. Family page: https://scenema.ai/styles/3d-product-animation - **[Botanical Glass 3D](https://scenema.ai/styles/3d-product-animation/botanical-glass-3d)**: Photoreal frosted glass products on raw concrete plinths, framed by living leaves and soft studio light. Thumbnail: https://cdn.scenema.ai/public/content/styles/botanical-glass-3d/scenes/inside-the-serum.webp - **[Cosmic Sand Epic](https://scenema.ai/styles/3d-product-animation/cosmic-sand-epic)**: Monumental cinematic 3D where every form is built from glittering sand and particle dust that forms and dissolves in deep space. Thumbnail: https://cdn.scenema.ai/public/content/styles/cosmic-sand-epic/scenes/anatomy-of-a-black-hole.webp - **[Dark Product Hero](https://scenema.ai/styles/3d-product-animation/dark-product-hero)**: A single sleek product in a black void, traced by studio rim light, with exploded views and minimal white type. Thumbnail: https://cdn.scenema.ai/public/content/styles/dark-product-hero/scenes/inside-the-earbud.webp - **[Sketch to Render](https://scenema.ai/styles/3d-product-animation/sketch-to-render)**: Every idea starts as a pencil sketch and becomes a polished photoreal render, split across the subject. Thumbnail: https://cdn.scenema.ai/public/content/styles/sketch-to-render/scenes/electric-scooter.webp ### Stop motion (4 styles) Clay figures, felt and miniature sets with the warmth of handmade animation. They make technical or medical topics feel friendly. Family page: https://scenema.ai/styles/stop-motion-animation - **[Claymation Characters](https://scenema.ai/styles/stop-motion-animation/claymation-characters)**: Handmade plasticine puppets with fingerprints and bead eyes, acting out stories on tiny cardboard and felt sets. Thumbnail: https://cdn.scenema.ai/public/content/styles/claymation-characters/scenes/how-compost-works.webp - **[Desert Miniature Diorama](https://scenema.ai/styles/stop-motion-animation/desert-miniature-diorama)**: Tactile miniature 3D sets of mid century desert homes at golden hour with puppet like figures. Thumbnail: https://cdn.scenema.ai/public/content/styles/desert-miniature-diorama/scenes/what-is-included.webp - **[Felt Craft Medical](https://scenema.ai/styles/stop-motion-animation/felt-craft-medical)**: Needle felted chibi dolls, stitched badges and fabric dioramas that turn health topics into friendly toys. Thumbnail: https://cdn.scenema.ai/public/content/styles/felt-craft-medical/scenes/how-your-heart-pumps.webp - **[Toy Chain Reaction](https://scenema.ai/styles/stop-motion-animation/toy-chain-reaction)**: Chunky 3D toys in turquoise and red set off chain reactions that show exactly how things work. Thumbnail: https://cdn.scenema.ai/public/content/styles/toy-chain-reaction/scenes/how-a-flush-works.webp ### 3D technical (3 styles) Cutaways, CAD renders and biomedical scenes that show what happens inside a machine or a body. Built for engineering, science and healthcare explainers. Family page: https://scenema.ai/styles/3d-technical-animation - **[Biomedical 3D](https://scenema.ai/styles/3d-technical-animation/biomedical-3d)**: Photoreal medical 3D: anatomy and cells with subsurface scattering, paired with sleek cyan HUD labels on deep navy. Thumbnail: https://cdn.scenema.ai/public/content/styles/biomedical-3d/scenes/how-insulin-works.webp - **[CAD Cutaway 3D](https://scenema.ai/styles/3d-technical-animation/cad-cutaway-3d)**: Technical 3D machinery in satin industrial blue and machined steel, opened up with exploded views, ghosted casings and leader line callouts. Thumbnail: https://cdn.scenema.ai/public/content/styles/cad-cutaway-3d/scenes/how-a-centrifugal-pump-works.webp - **[Toon 3D Cutaway](https://scenema.ai/styles/3d-technical-animation/toon-3d-cutaway)**: Bright, simplified 3D models cut open to show how things work, with parts coloured by function. Thumbnail: https://cdn.scenema.ai/public/content/styles/toon-3d-cutaway/scenes/how-a-fridge-works.webp ### Mixed media (3 styles) Real looking people and places with graphics drawn over them. Good for enterprise, health and brand stories that need a human face. Family page: https://scenema.ai/styles/mixed-media-explainer - **[Mixed Reality Enterprise](https://scenema.ai/styles/mixed-media-explainer/mixed-reality-enterprise)**: Real workplace photography with polished glowing overlays: traced outlines, glass data cards, HUD rings and flowing data lines. Thumbnail: https://cdn.scenema.ai/public/content/styles/mixed-reality-enterprise/scenes/wind-turbine-anatomy.webp - **[Mixed Reality Health](https://scenema.ai/styles/mixed-media-explainer/mixed-reality-health)**: Real photographs of everyday life with bold, glowing cartoon health characters living inside them, for friendly family explainers. Thumbnail: https://cdn.scenema.ai/public/content/styles/mixed-reality-health/scenes/feeding-your-gut-microbiome.webp - **[Colour Block Live Action](https://scenema.ai/styles/mixed-media-explainer/colour-block-live-action)**: Real people in bold single colour sets, with clean white interface cards and icons popping up around them. Thumbnail: https://cdn.scenema.ai/public/content/styles/colour-block-live-action/scenes/how-recognition-works.webp ### Isometric tech (3 styles) Flat isometric diagrams of servers, circuits and networks. A clear way to explain software, infrastructure and SaaS products. Family page: https://scenema.ai/styles/isometric-tech-explainer - **[Blueprint Circuit Isometric](https://scenema.ai/styles/isometric-tech-explainer/blueprint-circuit-isometric)**: White line isometric systems built on a deep cobalt grid, linked by glowing circuit traces. Thumbnail: https://cdn.scenema.ai/public/content/styles/blueprint-circuit-isometric/scenes/how-a-request-is-served.webp - **[Electric Blue SaaS Vector](https://scenema.ai/styles/isometric-tech-explainer/electric-blue-saas-vector)**: Lineless 2.5D vector characters and translucent dashboard cards on one saturated cobalt field. Thumbnail: https://cdn.scenema.ai/public/content/styles/electric-blue-saas-vector/scenes/spot-stalled-deals-early.webp - **[Neon Grid Isometric](https://scenema.ai/styles/isometric-tech-explainer/neon-grid-isometric)**: Dark mode 2.5D isometric trays in a black void, wired together by glowing cyan and violet circuit traces. Thumbnail: https://cdn.scenema.ai/public/content/styles/neon-grid-isometric/scenes/how-phishing-spreads.webp ### Collage (2 styles) Cut paper, old engravings and photos layered into moving collages. A strong look for essays, history and opinion pieces. Family page: https://scenema.ai/styles/collage-animation - **[Engraving Collage](https://scenema.ai/styles/collage-animation/engraving-collage)**: Vintage engravings cut out and recombined into surreal, witty scenes on deep teal with gold leaf and dusty rose. Thumbnail: https://cdn.scenema.ai/public/content/styles/engraving-collage/scenes/maslows-hierarchy.webp - **[Paper Cutout Collage](https://scenema.ai/styles/collage-animation/paper-cutout-collage)**: Grayscale photo cutouts, torn paper and halftone, punched up with saffron and teal shapes and giant numbers. Thumbnail: https://cdn.scenema.ai/public/content/styles/paper-cutout-collage/scenes/the-line-that-changed-work.webp ### Cinematic (2 styles) Photoreal scenes and documentary lighting for stories that need weight. Use them for documentaries, reenactments and brand films. Family page: https://scenema.ai/styles/cinematic-explainer - **[Cinematic Photoreal](https://scenema.ai/styles/cinematic-explainer/cinematic-photoreal)**: Real people, real places and real light, shot like a documentary on a cinema camera. Thumbnail: https://cdn.scenema.ai/public/content/styles/cinematic-photoreal/scenes/before-dawn-at-the-bakery.webp - **[Mannequin Documentary 3D](https://scenema.ai/styles/cinematic-explainer/mannequin-documentary-3d)**: Moody cinematic 3D with faceless grey mannequins, noir lighting, fog and god rays, for serious documentaries. Thumbnail: https://cdn.scenema.ai/public/content/styles/mannequin-documentary-3d/scenes/theodosian-walls.webp ### 3D tech (2 styles) Soft clay and glowing glass 3D worlds for software and startup stories. They turn abstract features into objects you can see. Family page: https://scenema.ai/styles/3d-saas-explainer - **[Clay Studio SaaS 3D](https://scenema.ai/styles/3d-saas-explainer/clay-studio-saas-3d)**: Glossy clay 3D props and floating app windows on soft periwinkle studio gradients. Thumbnail: https://cdn.scenema.ai/public/content/styles/clay-studio-saas-3d/scenes/one-click-cutouts.webp - **[Cyber Violet 3D](https://scenema.ai/styles/3d-saas-explainer/cyber-violet-3d)**: Glossy violet 3D with chrome, frosted glass cards and neon cyan and pink rim light in dark circuit tunnels. Thumbnail: https://cdn.scenema.ai/public/content/styles/cyber-violet-3d/scenes/how-passkeys-work.webp ### 3D characters (2 styles) Rounded 3D characters in matte and museum diorama worlds. They carry a story with the warmth of an animated film. Family page: https://scenema.ai/styles/3d-character-animation - **[Matte 3D Characters](https://scenema.ai/styles/3d-character-animation/matte-3d-characters)**: Friendly matte 3D: quirky alien characters, floating interface cards and glowing pedestals in a neon navy void. Thumbnail: https://cdn.scenema.ai/public/content/styles/matte-3d-characters/scenes/money-crosses-borders.webp - **[Warm Museum Diorama 3D](https://scenema.ai/styles/3d-character-animation/warm-museum-diorama-3d)**: Gentle stylized 3D characters in cutaway rooms of warm sand, satin wood and brushed gold. Thumbnail: https://cdn.scenema.ai/public/content/styles/warm-museum-diorama-3d/scenes/caring-for-the-collection.webp ### Blueprint (1 style) Technical drawings on blueprint paper that build themselves line by line. Made for engineering, architecture and how it works videos. Family page: https://scenema.ai/styles/blueprint-animation - **[Engineering Blueprint](https://scenema.ai/styles/blueprint-animation/engineering-blueprint)**: Technical line drawings on tinted engineering paper, with cutaways, leader line labels and dimension callouts. Thumbnail: https://cdn.scenema.ai/public/content/styles/engineering-blueprint/scenes/suspension-bridge-load.webp ## 23. Every voice All 501 narration voices, grouped by language. Each entry gives the voice name, gender, accent and a description of the voice and what it suits, followed by a link to its audio sample. Voices are cross lingual, so a voice can also narrate in other languages. Browse and listen on the [voices page](https://scenema.ai/voices). ### English (110 voices) - **Banjo** (male, en-AU): A bright, breezy Sydney man in his late thirties with a youthful, easygoing read. Great for travel stories, creator content and friendly brand videos. Sample: https://cdn.scenema.ai/public/content/voice/banjo/sample-pro-v2.mp3 - **Callum** (male, en-AU): A warm Sydney professor in his late fifties with conversational, slightly dry humour. Excellent for lectures, science lessons and thoughtful explainers. Sample: https://cdn.scenema.ai/public/content/voice/callum/sample-pro-v2.mp3 - **Hamish** (male, en-AU): An Australian man in his late thirties from Sydney with a calm, reflective and reassuring tone. He brings a thoughtful podcast feel to explainers and interviews. Sample: https://cdn.scenema.ai/public/content/voice/hamish/sample-pro-v2.mp3 - **Indi** (female, en-AU): An Australian woman in her early forties from Sydney who sounds confident and clear. Her research background suits data stories, science explainers and expert briefings. Sample: https://cdn.scenema.ai/public/content/voice/indi/sample-pro-v2.mp3 - **Jarrah** (male, en-AU): A low voiced Australian man in his mid thirties from Sydney with a curious, peer to peer style. Friendly and practical for recipes, how to videos and product demos. Sample: https://cdn.scenema.ai/public/content/voice/jarrah/sample-pro-v2.mp3 - **Liam** (male, en-AU): A low voiced Australian man in his mid forties from Sydney with a cool, confident and collaborative tone. Strong for research, technology and B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/liam/sample-pro-v2.mp3 - **Matilda** (female, en-AU): A deep, velvety Sydney woman in her late twenties with an unhurried podcast style. Great for interviews, commentary and relaxed brand storytelling. Sample: https://cdn.scenema.ai/public/content/voice/matilda/sample-pro-v2.mp3 - **Pippa** (female, en-AU): An Australian woman in her early forties from Sydney with a resonant, witty voice. Engaging and clear for training, onboarding and tutorials with personality. Sample: https://cdn.scenema.ai/public/content/voice/pippa/sample-pro-v2.mp3 - **Tahlia** (female, en-AU): An Australian woman in her late fifties from Sydney with a light, airy and precise delivery. Ideal for recipes, how to guides and friendly step by step training. Sample: https://cdn.scenema.ai/public/content/voice/tahlia/sample-pro-v2.mp3 - **Tessa** (female, en-AU): An Australian woman in her late thirties from Sydney with a cool, confident and collaborative manner. Supportive and clear for wellbeing, coaching and personal stories. Sample: https://cdn.scenema.ai/public/content/voice/tessa/sample-pro-v2.mp3 - **Arthur** (male, en-CA): A warm, engaging Vancouver man in his forties with a researcher's authority. Suited to B2B overviews, data stories and expert led product explainers. Sample: https://cdn.scenema.ai/public/content/voice/arthur/sample-pro-v2.mp3 - **Brooke** (female, en-CA): A confident young Canadian woman with a clear, upbeat read. Made for social ads, product launches and direct to consumer promos that need energy without hype. Sample: https://cdn.scenema.ai/public/content/voice/brooke/sample-pro-v2.mp3 - **Conrad** (male, en-CA): A young Toronto man with a natural, clear and low voice. Easygoing yet persuasive for social ads, tech promos and product launches. Sample: https://cdn.scenema.ai/public/content/voice/conrad/sample-pro-v2.mp3 - **Deborah** (female, en-CA): A Canadian woman in her early thirties from Vancouver with the warm, engaging manner of a librarian. Clear and inviting for lessons, book stories and explainers. Sample: https://cdn.scenema.ai/public/content/voice/deborah/sample-pro-v2.mp3 - **Emil** (male, en-CA): A low voiced Canadian man in his late forties from Toronto with an objective, direct and helpful style. Clear and fair for news, trivia and fact driven explainers. Sample: https://cdn.scenema.ai/public/content/voice/emil/sample-pro-v2.mp3 - **Ethan** (male, en-CA): A laid back, encouraging Vancouver man in his early thirties. Perfect for software tutorials, how to videos and onboarding that keep learners relaxed. Sample: https://cdn.scenema.ai/public/content/voice/ethan/sample-pro-v2.mp3 - **Piper** (female, en-CA): A bright young Canadian woman from Vancouver who sounds confident and clear. Built for social ads, app promos and product drops that need energy and charm. Sample: https://cdn.scenema.ai/public/content/voice/piper/sample-pro-v2.mp3 - **Riley** (female, en-CA): A young Toronto woman with a crisp, eager voice and a lower tone than you might expect. Perfect for trivia, listicles, quick explainers and fun social content. Sample: https://cdn.scenema.ai/public/content/voice/riley/sample-pro-v2.mp3 - **Shu** (female, en-CA): A clear, friendly Toronto woman in her early thirties. Made for software tutorials, onboarding and how to videos that feel welcoming and easy to follow. Sample: https://cdn.scenema.ai/public/content/voice/shu/sample-pro-v2.mp3 - **Simon** (male, en-CA): A low voiced Canadian man in his mid forties from Vancouver. Highly approachable and quietly philosophical, he makes big ideas easy to sit with. Sample: https://cdn.scenema.ai/public/content/voice/simon/sample-pro-v2.mp3 - **Amara** (female, en-GB): A young British woman from Newcastle with a highly approachable, professional voice. Warm and credible for legal, HR and policy explainers. Sample: https://cdn.scenema.ai/public/content/voice/amara/sample-pro-v2.mp3 - **Beatrice** (female, en-GB): An engaging, empathic Newcastle woman in her early forties with a lawyer's authority. Strong for legal rights, HR and public service explainers. Sample: https://cdn.scenema.ai/public/content/voice/beatrice/sample-pro-v2.mp3 - **Boonleng** (male, en-GB): A confident, clear Winchester man in his early thirties with a tutor's focus. Ideal for courses, software tutorials and science explainers. Sample: https://cdn.scenema.ai/public/content/voice/boonleng/sample-pro-v2.mp3 - **Cordelia** (female, en-GB): A resonant, witty Winchester woman in her early fifties. Perfect for nature documentaries, heritage stories and polished brand films with a classic English sound. Sample: https://cdn.scenema.ai/public/content/voice/cordelia/sample-pro-v2.mp3 - **Duncan** (male, en-GB): A crisp, eager Winchester man in his mid forties with a counsellor's warmth. Great for wellness, professional development and thoughtful explainers. Sample: https://cdn.scenema.ai/public/content/voice/duncan/sample-pro-v2.mp3 - **Eleanor** (female, en-GB): A warm, engaging Winchester woman in her late fifties with a teacher's patience. Perfect for courses, arts education and family friendly lessons. Sample: https://cdn.scenema.ai/public/content/voice/eleanor/sample-pro-v2.mp3 - **Emeka** (male, en-GB): A relaxed Newcastle man in his fifties with a friendly host style. Ideal for how to guides, cooking and hands on tutorials that feel easygoing. Sample: https://cdn.scenema.ai/public/content/voice/emeka/sample-pro-v2.mp3 - **Felix** (male, en-GB): A low voiced British man in his mid fifties from southern England. Confident and clear, he guides viewers through training, product tours and how to content. Sample: https://cdn.scenema.ai/public/content/voice/felix/sample-pro-v2.mp3 - **Freddie** (male, en-GB): A young man from southern England with a crisp, eager and low voice. Sharp and modern for social ads, tech launches and snappy brand promos. Sample: https://cdn.scenema.ai/public/content/voice/freddie/sample-pro-v2.mp3 - **Graham** (male, en-GB): A deep, velvety Bristol man in his mid fifties with an unhurried delivery. Excellent for nature documentaries, history and premium long form narration. Sample: https://cdn.scenema.ai/public/content/voice/graham/sample-pro-v2.mp3 - **Huiling** (female, en-GB): A bright young woman from Manchester with a warm, engaging coaching style. Full of personality for wellness programs, motivational content and lively character reads. Sample: https://cdn.scenema.ai/public/content/voice/huiling/sample-pro-v2.mp3 - **Maisie** (female, en-GB): A confident, clear woman in her early thirties with a warm Newcastle accent. She asks good questions and keeps listeners with her, ideal for podcasts, interviews and talk led explainers. Sample: https://cdn.scenema.ai/public/content/voice/maisie/sample-pro-v2.mp3 - **Miranda** (female, en-GB): A young professional woman from southern England with a measured, lawyerly clarity. Calm and approachable, she suits legal explainers, policy training and trusted financial content. Sample: https://cdn.scenema.ai/public/content/voice/miranda/sample-pro-v2.mp3 - **Nigel** (male, en-GB): A professional yet approachable Bristol man in his mid forties with a lawyer's steadiness. Strong for compliance, legal and corporate explainers. Sample: https://cdn.scenema.ai/public/content/voice/nigel/sample-pro-v2.mp3 - **Olivia** (female, en-GB): A comforting Manchester woman in her mid forties who sounds like a caring aunt. Ideal for wellness, patient guidance and gentle family stories. Sample: https://cdn.scenema.ai/public/content/voice/olivia/sample-pro-v2.mp3 - **Penelope** (female, en-GB): A textured, resonant Winchester woman in her late thirties with a soothing teacher's calm. Perfect for lessons, wellness and science explainers. Sample: https://cdn.scenema.ai/public/content/voice/penelope/sample-pro-v2.mp3 - **Rhys** (male, en-GB): A gentle, comforting Bristol man in his late twenties with a soft, steady tone. Ideal for wellness content, nature films and calm explainers. Sample: https://cdn.scenema.ai/public/content/voice/rhys/sample-pro-v2.mp3 - **Rosalind** (female, en-GB): A British woman in her mid sixties from southern England with a natural, clear and gracious voice. Steady and kind for training, tutorials and patient explainers. Sample: https://cdn.scenema.ai/public/content/voice/rosalind/sample-pro-v2.mp3 - **Rupert** (male, en-GB): A peer to peer, curious Newcastle man in his early forties with a trainer's energy. Great for fitness, wellness and conversational learning content. Sample: https://cdn.scenema.ai/public/content/voice/rupert/sample-pro-v2.mp3 - **Winston** (male, en-GB): A low voiced Manchester man in his late forties with the warm assurance of a trusted financial advisor. Grounded and credible for money, insurance and business explainers. Sample: https://cdn.scenema.ai/public/content/voice/winston/sample-pro-v2.mp3 - **Alistair** (male, en-IE): A low voiced Irish man in his late forties from Dublin with a close, reassuring bedside manner. Ideal for patient education, health explainers and trusted advice. Sample: https://cdn.scenema.ai/public/content/voice/alistair/sample-pro-v2.mp3 - **Clive** (male, en-IE): A textured, resonant Irish man in his late thirties from Dublin with a soothing bedside calm. Excellent for health, wellbeing and gentle expert explainers. Sample: https://cdn.scenema.ai/public/content/voice/clive/sample-pro-v2.mp3 - **Craig** (male, en-IE): A crisp, eager Dublin man in his fifties with a podcast host's curiosity. Great for commentary, current affairs and conversational explainers. Sample: https://cdn.scenema.ai/public/content/voice/craig/sample-pro-v2.mp3 - **Luna** (female, en-IE): A light, precise Dublin woman with an airy, gentle tone. Lovely for nature documentaries, calm explainers and travel stories with an Irish lilt. Sample: https://cdn.scenema.ai/public/content/voice/luna/sample-pro-v2.mp3 - **Orla** (female, en-IE): An Irish woman in her late forties from Dublin with the warm, assured voice of a journalist. Credible and engaging for news explainers, documentaries and reports. Sample: https://cdn.scenema.ai/public/content/voice/orla/sample-pro-v2.mp3 - **Ronald** (male, en-IE): A low voiced Irish man in his mid forties from Dublin with a curious, peer to peer style. Friendly and practical for cooking, how to and hospitality training. Sample: https://cdn.scenema.ai/public/content/voice/ronald/sample-pro-v2.mp3 - **Sophie** (female, en-IE): An Irish woman around forty from Dublin with an enthusiastic, engaging and fun style. She makes onboarding, tutorials and training modules feel like a good chat. Sample: https://cdn.scenema.ai/public/content/voice/sophie/sample-pro-v2.mp3 - **Victoria** (female, en-IE): An Irish woman in her late forties from Dublin with a light, airy and precise voice. Her character and charm suit nutrition tips, wellness coaching and playful stories. Sample: https://cdn.scenema.ai/public/content/voice/victoria/sample-pro-v2.mp3 - **Aditya** (male, en-IN): A low, warm Indian man in his mid forties with a seasoned radio host delivery. Natural and engaging for podcasts, news explainers and brand stories for India. Sample: https://cdn.scenema.ai/public/content/voice/aditya/sample-pro-v2.mp3 - **Anjali** (female, en-IN): An Indian woman in her late forties with the engaging, empathetic manner of a favourite professor. Clear and patient for lessons, explainers and course content. Sample: https://cdn.scenema.ai/public/content/voice/anjali/sample-pro-v2.mp3 - **Arjun** (male, en-IN): A precise, light voiced Indian man in his early fifties with a financial advisor's steadiness. Suited to banking, investment and insurance explainers. Sample: https://cdn.scenema.ai/public/content/voice/arjun/sample-pro-v2.mp3 - **Dhruv** (male, en-IN): A young Indian man with an energetic, colorful and fast voice. Lively for quick lessons, exam tips, tech explainers and YouTube education. Sample: https://cdn.scenema.ai/public/content/voice/dhruv/sample-pro-v2.mp3 - **Divya** (female, en-IN): A professional yet approachable Indian woman with a bright, high register. Strong for fintech explainers, personal finance lessons and banking onboarding. Sample: https://cdn.scenema.ai/public/content/voice/divya/sample-pro-v2.mp3 - **Kabir** (male, en-IN): A relaxed, low voiced Indian man around fifty with a senior lawyer's calm. Good for legal explainers, compliance and corporate policy videos. Sample: https://cdn.scenema.ai/public/content/voice/kabir/sample-pro-v2.mp3 - **Naomi** (female, en-IN): An Indian woman of sixty with the warm, engaging voice of a veteran radio host. Wise and trusted for health awareness, family stories and podcasts. Sample: https://cdn.scenema.ai/public/content/voice/naomi/sample-pro-v2.mp3 - **Rohan** (male, en-IN): A young Indian man with an enthusiastic, fun delivery and easy Hinglish rhythm. Made for social ads, app launches and youth focused promos. Sample: https://cdn.scenema.ai/public/content/voice/rohan/sample-pro-v2.mp3 - **Saanvi** (female, en-IN): A bright, empathetic Indian woman in her forties with a seasoned radio host style. She keeps podcasts, explainers and social stories lively and personal. Sample: https://cdn.scenema.ai/public/content/voice/saanvi/sample-pro-v2.mp3 - **Sarah** (female, en-IN): A young Indian woman with a bright, professional yet approachable voice. Upbeat and credible for social ads, fintech and beauty promos, and product launches. Sample: https://cdn.scenema.ai/public/content/voice/sarah/sample-pro-v2.mp3 - **Sunita** (female, en-IN): A highly approachable Indian woman in her late forties with a lawyer's clarity. Strong for legal rights explainers, compliance and policy guidance. Sample: https://cdn.scenema.ai/public/content/voice/sunita/sample-pro-v2.mp3 - **Vikram** (male, en-IN): A young Indian man with a light, precise and modern sound. Great for app ads, social promos and youth focused campaigns in Indian English. Sample: https://cdn.scenema.ai/public/content/voice/vikram/sample-pro-v2.mp3 - **Cooper** (male, en-NZ): A low voiced New Zealand man in his mid forties from Auckland with warm, engaging authority. Credible and calm for legal, policy and corporate explainers. Sample: https://cdn.scenema.ai/public/content/voice/cooper/sample-pro-v2.mp3 - **Junhao** (male, en-NZ): A New Zealand man in his early forties from Auckland with a broadcast ready, confident delivery. Great for training modules, product tours and clear how to videos. Sample: https://cdn.scenema.ai/public/content/voice/junhao/sample-pro-v2.mp3 - **Serene** (female, en-NZ): A New Zealand woman in her late thirties from Auckland with a cool, confident and collaborative manner. Trusted for legal, policy and professional explainers. Sample: https://cdn.scenema.ai/public/content/voice/serene/sample-pro-v2.mp3 - **Wiremu** (male, en-NZ): A low voiced New Zealand man in his late fifties from Auckland. Peer to peer and curious, he explores ideas alongside the listener in lessons and documentaries. Sample: https://cdn.scenema.ai/public/content/voice/wiremu/sample-pro-v2.mp3 - **Abby** (female, en-US): A peer to peer, curious Northwest woman in her mid twenties. Great for lessons, science explainers and creator content aimed at younger learners. Sample: https://cdn.scenema.ai/public/content/voice/abby/sample-pro-v2.mp3 - **Alaric** (male, en-US): An older American man from the West Coast with a low, intimate talk show warmth. He makes personal stories, essays and reflective narration feel like a conversation. Sample: https://cdn.scenema.ai/public/content/voice/alaric/sample-pro-v2.mp3 - **Amina** (female, en-US): A warm, engaging East Coast woman in her late fifties who sounds like a friendly stranger with a great story. Lovely for brand stories and history pieces. Sample: https://cdn.scenema.ai/public/content/voice/amina/sample-pro-v2.mp3 - **Andoy** (male, en-US): A friendly American man around thirty with a clear, low voice and East Coast crispness. A versatile pick for SaaS explainers, onboarding and courses. Sample: https://cdn.scenema.ai/public/content/voice/andoy/sample-pro-v2.mp3 - **Bianca** (female, en-US): A light, airy American woman with precise East Coast diction. She suits thoughtful video essays, philosophy explainers and calm documentary chapters. Sample: https://cdn.scenema.ai/public/content/voice/bianca/sample-pro-v2.mp3 - **Blake** (male, en-US): A comforting young Gulf Coast man in his early thirties with a lawyer's composure. Great for legal rights, insurance and customer support guidance. Sample: https://cdn.scenema.ai/public/content/voice/blake/sample-pro-v2.mp3 - **Brian** (male, en-US): A laid back, encouraging Northwest man in his mid thirties with a writing coach's warmth. Great for creative courses, tutorials and creator content. Sample: https://cdn.scenema.ai/public/content/voice/brian/sample-pro-v2.mp3 - **Camille** (female, en-US): A young American woman with a low, clear voice and a public radio composure. She suits explainers, lessons and news style recaps for younger audiences. Sample: https://cdn.scenema.ai/public/content/voice/camille/sample-pro-v2.mp3 - **Carter** (male, en-US): An enthusiastic, fun Northwest man in his mid forties with a radio host's energy. Great for podcasts, entertainment explainers and upbeat promos. Sample: https://cdn.scenema.ai/public/content/voice/carter/sample-pro-v2.mp3 - **Cedric** (male, en-US): A professional yet approachable Northwest man in his late thirties with a lawyer's grounding. Strong for legal, compliance and B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/cedric/sample-pro-v2.mp3 - **Chloe** (female, en-US): A soft, calm American woman with a gentle higher pitch. Soothing and personal for bedtime stories, meditations and quiet, heartfelt narration. Sample: https://cdn.scenema.ai/public/content/voice/chloe/sample-pro-v2.mp3 - **Dalisay** (female, en-US): A relaxed West Coast woman in her early thirties with a bright, friendly teacher's voice. Perfect for lessons, app tutorials and kids content. Sample: https://cdn.scenema.ai/public/content/voice/dalisay/sample-pro-v2.mp3 - **Damon** (male, en-US): An intimate, low voiced East Coast man in his early forties with a philosopher's depth. Great for video essays, thoughtful documentaries and reflective brand films. Sample: https://cdn.scenema.ai/public/content/voice/damon/sample-pro-v2.mp3 - **Darlene** (female, en-US): A professional yet approachable Gulf Coast woman in her early sixties with a veteran teacher's calm. Lovely for lessons, patient guidance and family content. Sample: https://cdn.scenema.ai/public/content/voice/darlene/sample-pro-v2.mp3 - **Elliot** (male, en-US): A low voiced American man of fifty from the Pacific Northwest with a warm, cinematic presence. He explains strategy and big ideas with patience and quiet drama. Sample: https://cdn.scenema.ai/public/content/voice/elliot/sample-pro-v2.mp3 - **Evelyn** (female, en-US): A light, precise American woman in her sixties with a relaxed West Coast tone. Gentle and wise for patient education, wellness and reflective explainers. Sample: https://cdn.scenema.ai/public/content/voice/evelyn/sample-pro-v2.mp3 - **Gareth** (male, en-US): A deep, velvety American man in his mid forties from the West Coast. Unhurried and inviting for cooking, how to guides and premium product walkthroughs. Sample: https://cdn.scenema.ai/public/content/voice/gareth/sample-pro-v2.mp3 - **Hana** (female, en-US): A confident, clear young woman from the Pacific Northwest with a bright, high register. Ideal for wellness ads, app promos and upbeat lifestyle spots. Sample: https://cdn.scenema.ai/public/content/voice/hana/sample-pro-v2.mp3 - **Harold** (male, en-US): A seasoned American man in his early sixties with a crisp, eager voice. Great for conversational stories, history pieces and video essays with lived in warmth. Sample: https://cdn.scenema.ai/public/content/voice/harold/sample-pro-v2.mp3 - **Jason** (male, en-US): A low, friendly American man with a Gulf Coast lilt and a professor's clarity. Good for courses, onboarding and explainers that should feel like a helpful chat. Sample: https://cdn.scenema.ai/public/content/voice/jason/sample-pro-v2.mp3 - **Jessica** (female, en-US): A warm, bright American woman with East Coast warmth and a podcast host's engagement. Great for courses, coaching content and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/jessica/sample-pro-v2.mp3 - **Lauren** (female, en-US): An objective, direct West Coast woman in her early forties with a financial advisor's clarity. Built for fintech, money lessons and B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/lauren/sample-pro-v2.mp3 - **Liwa** (female, en-US): A confident, clear Northwest woman in her late fifties with a bright teacher's voice. Excellent for lessons, how to guides and help center videos. Sample: https://cdn.scenema.ai/public/content/voice/liwa/sample-pro-v2.mp3 - **Marcus** (male, en-US): A comforting East Coast man in his mid forties with a lawyer's authority. Ideal for insurance, legal rights and patient guidance when stakes feel high. Sample: https://cdn.scenema.ai/public/content/voice/marcus/sample-pro-v2.mp3 - **Maricel** (female, en-US): A warm, engaging young woman from the inland South with a relaxed, homey feel. Lovely for family stories, food brands and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/maricel/sample-pro-v2.mp3 - **Marlene** (female, en-US): A low, confident American woman in her late fifties with an Inland Southern accent. Warm and stylish, she gives ads and brand spots a friendly, grown up charm. Sample: https://cdn.scenema.ai/public/content/voice/marlene/sample-pro-v2.mp3 - **Mia** (female, en-US): A young American woman with an Inland Southern accent and a natural, clear voice. Friendly and patient for lessons, kids learning and approachable explainers. Sample: https://cdn.scenema.ai/public/content/voice/mia/sample-pro-v2.mp3 - **Morgana** (female, en-US): A clear, direct American woman with a Pacific Northwest accent. Objective and helpful, she suits software tutorials, process walkthroughs and technical lessons. Sample: https://cdn.scenema.ai/public/content/voice/morgana/sample-pro-v2.mp3 - **Selene** (female, en-US): A young Gulf Coast woman with an intimate, talk show warmth and a stylist's flair. Great for beauty, fashion and lifestyle ads that feel personal. Sample: https://cdn.scenema.ai/public/content/voice/selene/sample-pro-v2.mp3 - **Serena** (female, en-US): An objective, direct Gulf Coast woman in her mid fifties with a documentary narrator's steadiness. Great for nature, science and environmental films. Sample: https://cdn.scenema.ai/public/content/voice/serena/sample-pro-v2.mp3 - **Tristan** (male, en-US): A low, confident American man with East Coast polish and a film narrator's presence. Built for documentaries, science lessons and authoritative explainers. Sample: https://cdn.scenema.ai/public/content/voice/tristan/sample-pro-v2.mp3 - **Tyler** (male, en-US): A fast paced, articulate Midwest man in his early fifties with a researcher's drive. Strong for tech explainers, data stories and product launches. Sample: https://cdn.scenema.ai/public/content/voice/tyler/sample-pro-v2.mp3 - **Veronica** (female, en-US): A low, cool American woman in her sixties with an East Coast finish. She narrates nature films and science stories with quiet confidence and an easy, collaborative warmth. Sample: https://cdn.scenema.ai/public/content/voice/veronica/sample-pro-v2.mp3 - **Vincent** (male, en-US): A resonant American man with a dry wit and a Pacific Northwest ease. He makes tutorials, strategy breakdowns and commentary videos feel smart and lively. Sample: https://cdn.scenema.ai/public/content/voice/vincent/sample-pro-v2.mp3 - **Vinny** (male, en-US): A fast paced, articulate Gulf Coast man in his late forties. Built for energetic retail ads, fashion promos and event spots that need drive. Sample: https://cdn.scenema.ai/public/content/voice/vinny/sample-pro-v2.mp3 - **Warren** (male, en-US): A confident, clear Northwest man in his mid thirties with a radio host's polish. Strong for podcasts, news explainers and product overviews. Sample: https://cdn.scenema.ai/public/content/voice/warren/sample-pro-v2.mp3 - **Wei** (male, en-US): A young American man with a low, steady voice and Pacific Northwest calm. Confident and clear for software tutorials, app explainers and study content. Sample: https://cdn.scenema.ai/public/content/voice/wei/sample-pro-v2.mp3 - **Zherong** (male, en-US): A relaxed West Coast man in his late forties with a writing tutor's patience. Ideal for courses, video essays and thoughtful how to content. Sample: https://cdn.scenema.ai/public/content/voice/zherong/sample-pro-v2.mp3 - **Chioma** (female, en-ZA): A South African woman of sixty from Cape Town whose bright, breezy voice sounds far younger. Stylish and upbeat for fashion, beauty and lifestyle ads. Sample: https://cdn.scenema.ai/public/content/voice/chioma/sample-pro-v2.mp3 - **Eldrin** (male, en-ZA): A South African man in his early forties from Cape Town with an energetic, colorful and fast delivery. Bold and fun for retail ads, promos and event trailers. Sample: https://cdn.scenema.ai/public/content/voice/eldrin/sample-pro-v2.mp3 - **Folake** (female, en-ZA): A South African woman in her early forties from Cape Town with a natural, clear storytelling voice. Easy and engaging for stories, brand films and community content. Sample: https://cdn.scenema.ai/public/content/voice/folake/sample-pro-v2.mp3 - **Jaco** (male, en-ZA): A young South African man from Cape Town with a warm, engaging and radio ready voice. Patient and friendly for lessons, music education and calm explainers. Sample: https://cdn.scenema.ai/public/content/voice/jaco/sample-pro-v2.mp3 - **Lindiwe** (female, en-ZA): A young South African woman from Cape Town who sounds confident, clear and patient. A good fit for lessons, writing guides and calm educational explainers. Sample: https://cdn.scenema.ai/public/content/voice/lindiwe/sample-pro-v2.mp3 - **Sipho** (male, en-ZA): A relaxed South African man around thirty from Cape Town who tells stories like a favourite uncle. Easygoing and friendly for stories, community films and casual explainers. Sample: https://cdn.scenema.ai/public/content/voice/sipho/sample-pro-v2.mp3 - **Tunde** (male, en-ZA): A professional yet approachable Cape Town man in his late forties. Strong for training videos, how to guides and onboarding that needs a steady, friendly lead. Sample: https://cdn.scenema.ai/public/content/voice/tunde/sample-pro-v2.mp3 - **Zanele** (female, en-ZA): An objective, direct South African woman with a doctor's calm authority. Built for patient education, healthcare explainers and clear professional guidance. Sample: https://cdn.scenema.ai/public/content/voice/zanele/sample-pro-v2.mp3 ### Spanish (34 voices) - **Borja** (male, es-419): A low, warm Argentine man with a stylish, persuasive polish. Fits premium brand stories, fashion and lifestyle ads and confident product launches. Sample: https://cdn.scenema.ai/public/content/voice/borja/sample-pro-v2.mp3 - **Bruno** (male, es-419): A low, professional yet approachable Mexican man in his fifties with a TV host's ease. Strong for recipe videos, hospitality training and practical how tos. Sample: https://cdn.scenema.ai/public/content/voice/bruno/sample-pro-v2.mp3 - **Camila** (female, es-419): A young Mexican woman with a surprisingly deep, velvety and unhurried voice. Strong for premium beauty, lifestyle and brand ads that want allure over hype. Sample: https://cdn.scenema.ai/public/content/voice/camila/sample-pro-v2.mp3 - **Citlali** (female, es-419): A low, highly approachable Mexican woman with a professor's grounding. A natural fit for courses, patient education and public information in Mexican Spanish. Sample: https://cdn.scenema.ai/public/content/voice/citlali/sample-pro-v2.mp3 - **Cuauhtemoc** (male, es-419): A young Mexican man with a textured, resonant and soothing voice and a reality TV flair. Suits character narration, creator content and lifestyle promos. Sample: https://cdn.scenema.ai/public/content/voice/cuauhtemoc/sample-pro-v2.mp3 - **Diego** (male, es-419): A low, textured and soothing Mexican man with a nutritionist's grounded advice. Great for health, nutrition and wellness content in Mexican Spanish. Sample: https://cdn.scenema.ai/public/content/voice/diego/sample-pro-v2.mp3 - **Graciela** (female, es-419): A bright, breezy Argentine woman in her sixties with a mentor's warmth and a youthful lift. Lovely for coaching, wellness and inspiring personal stories. Sample: https://cdn.scenema.ai/public/content/voice/graciela/sample-pro-v2.mp3 - **Guadalupe** (female, es-419): A confident, clear Argentine woman with a therapist's insight and a podcast host's flow. Great for wellness, HR and personal development content. Sample: https://cdn.scenema.ai/public/content/voice/guadalupe/sample-pro-v2.mp3 - **Itzel** (female, es-419): A young Mexican woman with a low, intimate talk show warmth. Lovely for recipe videos, lifestyle how tos and friendly product demos in Mexican Spanish. Sample: https://cdn.scenema.ai/public/content/voice/itzel/sample-pro-v2.mp3 - **Lupita** (female, es-419): A bright, confident young Mexican woman with influencer energy. Built for social ads, product launches and upbeat e-commerce videos in Mexican Spanish. Sample: https://cdn.scenema.ai/public/content/voice/lupita/sample-pro-v2.mp3 - **Mateo** (male, es-419): A young Mexican man with a low, professional yet approachable tone. Works for brand ads, app launches and explainer style commercials in Mexican Spanish. Sample: https://cdn.scenema.ai/public/content/voice/mateo/sample-pro-v2.mp3 - **Mauricio** (male, es-419): A low, confident Argentine man in his sixties with a veteran interviewer's calm. Suited to podcasts, documentaries and thoughtful commentary in Rioplatense Spanish. Sample: https://cdn.scenema.ai/public/content/voice/mauricio/sample-pro-v2.mp3 - **Maximiliano** (male, es-419): A young Argentine man with a low, easygoing voice that sounds like a friend on the bus. Natural for casual explainers, creator content and app walkthroughs. Sample: https://cdn.scenema.ai/public/content/voice/maximiliano/sample-pro-v2.mp3 - **Mayte** (female, es-419): A young Argentine woman with a bright, high voice and confident clarity. Great for lessons, kids and family learning, and lively explainers in Rioplatense Spanish. Sample: https://cdn.scenema.ai/public/content/voice/mayte/sample-pro-v2.mp3 - **Miguel** (male, es-419): A low, natural Argentine man in his late fifties with a therapist's calm. Ideal for mental health, reflective storytelling and gentle health explainers. Sample: https://cdn.scenema.ai/public/content/voice/miguel/sample-pro-v2.mp3 - **Paloma** (female, es-419): A low, natural Argentine woman with a parent's warmth and clear, everyday speech. Fits family content, health information and friendly customer explainers. Sample: https://cdn.scenema.ai/public/content/voice/paloma/sample-pro-v2.mp3 - **Rafael** (male, es-419): A low, warm Argentine man with a lawyer's credibility and a relaxed, homey tone. Good for legal rights, insurance and HR explainers that need trust and warmth. Sample: https://cdn.scenema.ai/public/content/voice/rafael/sample-pro-v2.mp3 - **Ruben** (male, es-419): A warm, engaging Argentine man with a low voice and a podcast host's ease. A good fit for lessons, finance explainers and longer educational videos. Sample: https://cdn.scenema.ai/public/content/voice/ruben/sample-pro-v2.mp3 - **Salvador** (male, es-419): A warm, engaging Argentine man with a medium voice and a radio analyst's clarity. Good for B2B overviews, news analysis and expert explainers. Sample: https://cdn.scenema.ai/public/content/voice/salvador/sample-pro-v2.mp3 - **Sergio** (male, es-419): A low, confident Argentine man with a financial advisor's steadiness. A strong pick for fintech, insurance and money explainers in Rioplatense Spanish. Sample: https://cdn.scenema.ai/public/content/voice/sergio/sample-pro-v2.mp3 - **Sofia** (female, es-419): A bright, professional yet approachable Mexican woman with a lawyer's clarity. Good for legal, finance and B2B explainers that should feel accessible. Sample: https://cdn.scenema.ai/public/content/voice/sofia/sample-pro-v2.mp3 - **Valeria** (female, es-419): A calm, reflective Argentine woman with a lawyer's precision and a reassuring tone. Strong for legal, insurance and healthcare explainers in Rioplatense Spanish. Sample: https://cdn.scenema.ai/public/content/voice/valeria/sample-pro-v2.mp3 - **Ximena** (female, es-419): A young Argentine woman with an objective, direct radio host delivery. Fits news recaps, data stories and helpful explainers in Rioplatense Spanish. Sample: https://cdn.scenema.ai/public/content/voice/ximena/sample-pro-v2.mp3 - **Xochitl** (female, es-419): A confident, clear Argentine woman with a teacher's poise and a cinematic polish. Strong for courses, documentaries and explainers in Rioplatense Spanish. Sample: https://cdn.scenema.ai/public/content/voice/xochitl/sample-pro-v2.mp3 - **Alvaro** (male, es-ES): A young, confident man from Spain with a low voice and a brainstorming energy. Good for software tutorials, app demos and startup explainers in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/alvaro/sample-pro-v2.mp3 - **Curro** (male, es-ES): A low, credible man from Spain with a lawyer's precision and a curious, peer to peer tone. Suited to legal, finance and B2B explainers in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/curro/sample-pro-v2.mp3 - **Gonzalo** (male, es-ES): A warm, engaging man from Spain with a low voice and a TV host's ease. Great for recipe videos, travel and hospitality content and friendly training. Sample: https://cdn.scenema.ai/public/content/voice/gonzalo/sample-pro-v2.mp3 - **Ignacio** (male, es-ES): A low, calm and confident man from Spain with a lawyer's measured clarity. Fits legal, compliance and corporate explainers in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/ignacio/sample-pro-v2.mp3 - **Inmaculada** (female, es-ES): A warm, engaging woman from Spain with a polished radio feel. Strong for brand stories, commercials and product launches in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/inmaculada/sample-pro-v2.mp3 - **Joaquin** (male, es-ES): A natural, clear man from Spain with a cooking show host's ease. Great for how to guides, recipes, product demos and training videos in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/joaquin/sample-pro-v2.mp3 - **Marta** (female, es-ES): A clear, friendly woman from Spain with a bright register and an instructional host's patience. Ideal for tutorials, onboarding and e-learning in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/marta/sample-pro-v2.mp3 - **Mercedes** (female, es-ES): A resonant, witty woman from Spain with the ease of a veteran radio host. Ideal for podcasts, commentary and conversational explainers in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/mercedes/sample-pro-v2.mp3 - **Pilar** (female, es-ES): A fast, articulate and energetic woman from Spain. Built for punchy social ads, promos and product launches that need quick hooks in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/pilar/sample-pro-v2.mp3 - **Rocio** (female, es-ES): A warm, intimate woman from Spain with a talk show closeness. Suited to wellness, personal stories and reflective explainers in Castilian Spanish. Sample: https://cdn.scenema.ai/public/content/voice/rocio/sample-pro-v2.mp3 ### Chinese (Mandarin) (25 voices) - **Guilan** (female, zh): A professional yet approachable mature female voice in Mandarin with a bright, gentle tone. Lovely for stories, family content and brand narratives. Sample: https://cdn.scenema.ai/public/content/voice/guilan/sample-pro-v2.mp3 - **Guoqiang** (male, zh): A cool, confident and collaborative mature male voice in Mandarin with a low tone. Made for workplace training, tutorials and process walkthroughs. Sample: https://cdn.scenema.ai/public/content/voice/guoqiang/sample-pro-v2.mp3 - **Haoran** (male, zh): An enthusiastic, fun young male voice in Mandarin with an expressive coaching style. Great for lifestyle content, character reads and social ads. Sample: https://cdn.scenema.ai/public/content/voice/haoran/sample-pro-v2.mp3 - **Jiahao** (male, zh): A professional yet approachable male voice in Mandarin with a low, persuasive tone. Built for advocacy, brand campaigns and calls to action. Sample: https://cdn.scenema.ai/public/content/voice/jiahao/sample-pro-v2.mp3 - **Jianguo** (male, zh): A confident, clear male voice in Mandarin with a low, newsroom steadiness. Built for news, current affairs and serious explainers. Sample: https://cdn.scenema.ai/public/content/voice/jianguo/sample-pro-v2.mp3 - **Jianhua** (male, zh): A cool, confident male voice in Mandarin with a low, collaborative warmth. Suited to wellness content, stories and thoughtful explainers. Sample: https://cdn.scenema.ai/public/content/voice/jianhua/sample-pro-v2.mp3 - **Jing** (female, zh): A warm young female voice in Mandarin with a bright tone and a touch of dry humor. Ideal for lessons, science explainers and friendly tutorials. Sample: https://cdn.scenema.ai/public/content/voice/jing/sample-pro-v2.mp3 - **Lingyun** (female, zh): A light, airy and precise female voice in Mandarin with a bright tone. Great for trivia, quick explainers and app walkthroughs. Sample: https://cdn.scenema.ai/public/content/voice/lingyun/sample-pro-v2.mp3 - **Mei** (female, zh): A confident, clear female voice in Mandarin with a calm documentary feel. Ideal for nature films, science explainers and sustainability stories. Sample: https://cdn.scenema.ai/public/content/voice/mei/sample-pro-v2.mp3 - **Ming** (male, zh): A clear, friendly young male voice in Mandarin with a low, gentle tone. Suited to nature documentaries, science and calm explainers. Sample: https://cdn.scenema.ai/public/content/voice/ming/sample-pro-v2.mp3 - **Ruoxi** (female, zh): A confident, clear female voice in Mandarin with a polished, cinematic presence. Great for podcasts, brand films and video essays. Sample: https://cdn.scenema.ai/public/content/voice/ruoxi/sample-pro-v2.mp3 - **Shiyun** (female, zh): A peer to peer, curious female voice in Mandarin with a mid range, stylish tone. Suited to fashion, beauty and lifestyle ads. Sample: https://cdn.scenema.ai/public/content/voice/shiyun/sample-pro-v2.mp3 - **Shuhua** (female, zh): A cool, confident senior female voice in Mandarin with a bright, refined tone. Ideal for lessons, literature, culture and mentoring content. Sample: https://cdn.scenema.ai/public/content/voice/shuhua/sample-pro-v2.mp3 - **Tianyu** (male, zh): An objective, direct and helpful male voice in Mandarin with a mid range tone. Ideal for trivia, explainers and fact driven videos. Sample: https://cdn.scenema.ai/public/content/voice/tianyu/sample-pro-v2.mp3 - **Weiming** (male, zh): An objective, direct and helpful male voice in Mandarin with a low, clinical calm. Built for medical, pharma and patient education videos. Sample: https://cdn.scenema.ai/public/content/voice/weiming/sample-pro-v2.mp3 - **Wenjing** (female, zh): An objective, direct female voice in Mandarin with a bright, precise tone. Built for legal, compliance and policy explainers. Sample: https://cdn.scenema.ai/public/content/voice/wenjing/sample-pro-v2.mp3 - **Xiaoyin** (female, zh): A clear, friendly young female voice in Mandarin with a bright, cheerful tone. Made for cooking, how to and product tutorial videos. Sample: https://cdn.scenema.ai/public/content/voice/xiaoyin/sample-pro-v2.mp3 - **Xiaoyu** (female, zh): A confident, clear young female voice in Mandarin with a bright, sharp tone. Made for tech, AI and data explainers and B2B overviews. Sample: https://cdn.scenema.ai/public/content/voice/xiaoyu/sample-pro-v2.mp3 - **Xinyi** (female, zh): A professional yet approachable female voice in Mandarin with a bright, melodic tone. Ideal for lessons, kids learning and arts education. Sample: https://cdn.scenema.ai/public/content/voice/xinyi/sample-pro-v2.mp3 - **Yichen** (male, zh): A comforting male voice in Mandarin with a low, patient tone. Made for training videos, onboarding and calm step by step tutorials. Sample: https://cdn.scenema.ai/public/content/voice/yichen/sample-pro-v2.mp3 - **Yifan** (male, zh): A warm, engaging male voice in Mandarin with a low, friendly tone. Lovely for stories, family content and relaxed explainers. Sample: https://cdn.scenema.ai/public/content/voice/yifan/sample-pro-v2.mp3 - **Yiling** (female, zh): A professional yet approachable female voice in Mandarin with a low, centered tone. Great for fitness, wellness podcasts and lifestyle content. Sample: https://cdn.scenema.ai/public/content/voice/yiling/sample-pro-v2.mp3 - **Yutong** (female, zh): A deep, velvety and unhurried young female voice in Mandarin. Suited to premium beauty, fashion and lifestyle ads with a polished feel. Sample: https://cdn.scenema.ai/public/content/voice/yutong/sample-pro-v2.mp3 - **Zhiwei** (male, zh): A warm, engaging male voice in Mandarin with a low, trustworthy tone. Built for finance, insurance and business explainers. Sample: https://cdn.scenema.ai/public/content/voice/zhiwei/sample-pro-v2.mp3 - **Zihan** (male, zh): A professional yet approachable male voice in Mandarin with a low, reflective tone. Ideal for video essays, history and thoughtful documentaries. Sample: https://cdn.scenema.ai/public/content/voice/zihan/sample-pro-v2.mp3 ### Hindi (24 voices) - **Balwant** (male, hi): A low, confident Hindi voice of a veteran fitness coach in his sixties. Great for fitness, healthy aging and motivational wellness content. Sample: https://cdn.scenema.ai/public/content/voice/balwant/sample-pro-v2.mp3 - **Aanya** (female, hi-IN): A bright, highly approachable woman who explains money matters. Great for Hindi fintech onboarding, savings tips and insurance videos for everyday families. Sample: https://cdn.scenema.ai/public/content/voice/aanya/sample-pro-v2.mp3 - **Aarav** (male, hi-IN): A mature, low male voice that sounds confident and clear. Perfect for heartfelt Hindi stories, history and wellness narration with the calm of a seasoned counselor. Sample: https://cdn.scenema.ai/public/content/voice/aarav/sample-pro-v2.mp3 - **Ajay** (male, hi-IN): A mature, low male voice with a professional yet approachable manner. Built for training modules, how to videos and long course content in polished Delhi Hindi. Sample: https://cdn.scenema.ai/public/content/voice/ajay/sample-pro-v2.mp3 - **Amit** (male, hi-IN): A low male voice that is objective, direct and helpful. Made for Hindi personal finance, investing and banking explainers that respect the viewer's time. Sample: https://cdn.scenema.ai/public/content/voice/amit/sample-pro-v2.mp3 - **Ankit** (male, hi-IN): A young, low Hindi speaking man with a professional yet approachable host style. Great for recipe videos, how to guides and app tutorials in Hindi. Sample: https://cdn.scenema.ai/public/content/voice/ankit/sample-pro-v2.mp3 - **Ishaan** (male, hi-IN): A low, professional male voice with an approachable manner. Suited to legal explainers, insurance and banking videos where Hindi viewers need to trust what they hear. Sample: https://cdn.scenema.ai/public/content/voice/ishaan/sample-pro-v2.mp3 - **Ishita** (female, hi-IN): A bright young woman who narrates with confidence and clarity. Suited to Hindi nature and science documentaries and curious explainer channels. Sample: https://cdn.scenema.ai/public/content/voice/ishita/sample-pro-v2.mp3 - **Kamla** (female, hi-IN): A warm, engaging Hindi speaking woman in her sixties with a bright voice and a veteran interviewer's curiosity. Lovely for podcasts, social stories and civic content. Sample: https://cdn.scenema.ai/public/content/voice/kamla/sample-pro-v2.mp3 - **Kirti** (female, hi-IN): A comforting woman's voice for calm Hindi narration. Suited to wellness, nature and health videos that should help viewers relax and feel cared for. Sample: https://cdn.scenema.ai/public/content/voice/kirti/sample-pro-v2.mp3 - **Manoj** (male, hi-IN): A mature, low male voice that sounds confident and clear. Built for serious Hindi documentaries, history and science narration with gravitas. Sample: https://cdn.scenema.ai/public/content/voice/manoj/sample-pro-v2.mp3 - **Meher** (female, hi-IN): A bright, breezy young woman with a Delhi Hindustani lilt. Great for stories, faceless channels and friendly app explainers that need lightness and charm. Sample: https://cdn.scenema.ai/public/content/voice/meher/sample-pro-v2.mp3 - **Neha** (female, hi-IN): A low, comforting female voice with a professional calm. Suited to legal, health and insurance videos where Hindi viewers may feel stressed and need reassurance. Sample: https://cdn.scenema.ai/public/content/voice/neha/sample-pro-v2.mp3 - **Nikhil** (male, hi-IN): A resonant male voice with a quick, witty edge. Ideal for Hindi video essays, writing lessons and explainers that need personality as well as clarity. Sample: https://cdn.scenema.ai/public/content/voice/nikhil/sample-pro-v2.mp3 - **Pooja** (female, hi-IN): A comforting Hindi speaking woman with a nature documentary calm and a soft central Indian warmth. Ideal for documentaries, lessons and gentle health content. Sample: https://cdn.scenema.ai/public/content/voice/pooja/sample-pro-v2.mp3 - **Rahul** (male, hi-IN): A relaxed, low Delhi voice with refined Urdu inflection and a financial advisor's credibility. Strong for fintech, insurance and money explainers in Hindi. Sample: https://cdn.scenema.ai/public/content/voice/rahul/sample-pro-v2.mp3 - **Rajesh** (male, hi-IN): A mature, low male voice that sounds confident and clear. Built for premium Hindi brand films, product launches and refined commercial spots. Sample: https://cdn.scenema.ai/public/content/voice/rajesh/sample-pro-v2.mp3 - **Rekha** (female, hi-IN): A bright, confident woman in her fifties who explains clearly. Made for cooking, home and how to videos and friendly training content in Hindi. Sample: https://cdn.scenema.ai/public/content/voice/rekha/sample-pro-v2.mp3 - **Riya** (female, hi-IN): A highly approachable woman in her forties with the ease of a podcast host. Great for conversational Hindi explainers, news style videos and interviews. Sample: https://cdn.scenema.ai/public/content/voice/riya/sample-pro-v2.mp3 - **Sanjay** (male, hi-IN): A low male voice with a surprisingly bright, breezy energy. Suited to Hindi travel, nature and lifestyle documentaries that should feel open and inviting. Sample: https://cdn.scenema.ai/public/content/voice/sanjay/sample-pro-v2.mp3 - **Seema** (female, hi-IN): A bright, helpful young Hindi woman with a gentle Awadhi flavour. Objective and direct, she suits travel guides, service walkthroughs and clear customer information. Sample: https://cdn.scenema.ai/public/content/voice/seema/sample-pro-v2.mp3 - **Shreya** (female, hi-IN): A bright, young Hindi speaking woman with influencer energy and a polished, approachable tone. Built for social ads, product launches and e-commerce promos. Sample: https://cdn.scenema.ai/public/content/voice/shreya/sample-pro-v2.mp3 - **Sumit** (male, hi-IN): A young man with a low, comforting voice who explains patiently. Great for Hindi lessons, coding and app tutorials aimed at students who feel stuck. Sample: https://cdn.scenema.ai/public/content/voice/sumit/sample-pro-v2.mp3 - **Tanvi** (female, hi-IN): A light, airy and precise female voice for fashion, beauty and ecommerce ads in stylish Delhi Hindi. Clean and polished for short commercial spots. Sample: https://cdn.scenema.ai/public/content/voice/tanvi/sample-pro-v2.mp3 ### Russian (21 voices) - **Alyona** (female, ru): A calm, reassuring female voice in her forties for Russian podcasts, interview shows and thoughtful commentary. Her reflective delivery keeps long episodes easy to follow. Sample: https://cdn.scenema.ai/public/content/voice/alyona/sample-pro-v2.mp3 - **Anastasia** (female, ru): A composed, reassuring female voice in her early thirties for Russian legal, compliance and finance explainers. She makes rules and rights sound clear and calm. Sample: https://cdn.scenema.ai/public/content/voice/anastasia/sample-pro-v2.mp3 - **Arkady** (male, ru): A young, engaging male voice in his twenties for Russian quiz shows, fun facts channels and podcasts. Empathic and lively, he makes trivia feel like a conversation. Sample: https://cdn.scenema.ai/public/content/voice/arkady/sample-pro-v2.mp3 - **Darya** (female, ru): A confident, clear young female voice in Russian with a bright, energetic tone. Suited to social ads, app promos and product launches. Sample: https://cdn.scenema.ai/public/content/voice/darya/sample-pro-v2.mp3 - **Dmitry** (male, ru): A laid back, encouraging senior male voice in Russian with a mid range tone. Built for financial guidance, retirement and trusted advice. Sample: https://cdn.scenema.ai/public/content/voice/dmitry/sample-pro-v2.mp3 - **Elena** (female, ru): A warm, engaging female voice in Russian with a low, rich tone. Ideal for trivia, faceless channels and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/elena/sample-pro-v2.mp3 - **Galina** (female, ru): A clear, confident female voice in her mid fifties for Russian lessons, school content and public information. Experienced and warm, she explains with practiced ease. Sample: https://cdn.scenema.ai/public/content/voice/galina/sample-pro-v2.mp3 - **Gleb** (male, ru): An upbeat, cheerful male voice with a rich, approachable tone for Russian podcasts, entertainment content and ads. He brings energy and good humor to every script. Sample: https://cdn.scenema.ai/public/content/voice/gleb/sample-pro-v2.mp3 - **Lev** (male, ru): A grounded male voice in his thirties for Russian software tutorials, onboarding and how to videos. Professional and approachable, he walks viewers through each step without rushing. Sample: https://cdn.scenema.ai/public/content/voice/lev/sample-pro-v2.mp3 - **Oksana** (female, ru): A confident, clear female voice in Russian with a low, academic tone. Ideal for lectures, science and history explainers. Sample: https://cdn.scenema.ai/public/content/voice/oksana/sample-pro-v2.mp3 - **Polina** (female, ru): A gentle, soothing female voice in her mid twenties for Russian wellness, mental health and patient education content. Calm and reflective, she helps listeners feel safe. Sample: https://cdn.scenema.ai/public/content/voice/polina/sample-pro-v2.mp3 - **Rodion** (male, ru): A cool, confident male voice in his forties for Russian courses, science lectures and tech explainers. Collaborative and clear, he teaches like a favorite professor. Sample: https://cdn.scenema.ai/public/content/voice/rodion/sample-pro-v2.mp3 - **Ruslan** (male, ru): A resonant, witty senior male voice in Russian with a low, lively tone. Made for cooking shows, how to videos and warm tutorials. Sample: https://cdn.scenema.ai/public/content/voice/ruslan/sample-pro-v2.mp3 - **Snezhana** (female, ru): A bright, warm female voice in her early thirties for Russian social ads, product promos and app launches. Engaging and lively, she brings a friendly spark to short spots. Sample: https://cdn.scenema.ai/public/content/voice/snezhana/sample-pro-v2.mp3 - **Stepan** (male, ru): A wise, warm male voice near sixty for Russian documentaries, history and video essays. His low, unhurried delivery gives ideas room to breathe. Sample: https://cdn.scenema.ai/public/content/voice/stepan/sample-pro-v2.mp3 - **Svetlana** (female, ru): A credible, articulate female voice in her forties for Russian science, medical and B2B explainers. Professional yet approachable, she presents findings with quiet authority. Sample: https://cdn.scenema.ai/public/content/voice/svetlana/sample-pro-v2.mp3 - **Tamara** (female, ru): A confident, clear mature female voice in Russian with a low, gracious tone. Great for event promos, hospitality and podcast style content. Sample: https://cdn.scenema.ai/public/content/voice/tamara/sample-pro-v2.mp3 - **Timofey** (male, ru): A clear, friendly male voice in Russian with a low, steady tone. Built for legal, finance and corporate explainers that need warmth. Sample: https://cdn.scenema.ai/public/content/voice/timofey/sample-pro-v2.mp3 - **Vadim** (male, ru): A cool, confident and collaborative mature male voice in Russian. Great for fitness and wellness coaching, motivation and character reads. Sample: https://cdn.scenema.ai/public/content/voice/vadim/sample-pro-v2.mp3 - **Yegor** (male, ru): A patient, warm male voice in his early thirties for Russian lessons, strategy breakdowns and educational YouTube. He makes complex ideas feel manageable. Sample: https://cdn.scenema.ai/public/content/voice/yegor/sample-pro-v2.mp3 - **Yulia** (female, ru): A warm, curious female voice in her forties for Russian how to videos, recipe content and product guides. She speaks peer to peer, like a friend showing you around her kitchen. Sample: https://cdn.scenema.ai/public/content/voice/yulia/sample-pro-v2.mp3 ### Arabic (20 voices) - **Adel** (male, ar-001): A low, assured Arabic man in his late fifties speaking clear Modern Standard Arabic. He brings calm, caring confidence to social, civic and health topics. Sample: https://cdn.scenema.ai/public/content/voice/adel/sample-pro-v2.mp3 - **Ashraf** (male, ar-001): A low, polished Arabic man in his late forties speaking clear Modern Standard Arabic. He sounds like a public radio presenter, professional yet approachable. Sample: https://cdn.scenema.ai/public/content/voice/ashraf/sample-pro-v2.mp3 - **Dina** (female, ar-001): A bright, confident Arabic woman in her late thirties speaking clear Modern Standard Arabic. She leads wellness, fitness and training content with a motivating, assured voice. Sample: https://cdn.scenema.ai/public/content/voice/dina/sample-pro-v2.mp3 - **Heba** (female, ar-001): A bright, intimate Arabic woman around forty speaking clear Modern Standard Arabic. She talks to viewers like a talk show host, close and personal. Sample: https://cdn.scenema.ai/public/content/voice/heba/sample-pro-v2.mp3 - **Karim** (male, ar-001): A young male voice in professional yet approachable Modern Standard Arabic. Made for corporate training, software tutorials and onboarding across Arab markets. Sample: https://cdn.scenema.ai/public/content/voice/karim/sample-pro-v2.mp3 - **Lina** (female, ar-001): A bright, breezy young woman in Modern Standard Arabic. Great for cooking, how to and onboarding videos that should feel light and welcoming. Sample: https://cdn.scenema.ai/public/content/voice/lina/sample-pro-v2.mp3 - **Mona** (female, ar-001): A bright, warm Arabic woman in her early fifties speaking clear Modern Standard Arabic. She explains health, wellness and learning topics with an engaging radio warmth. Sample: https://cdn.scenema.ai/public/content/voice/mona/sample-pro-v2.mp3 - **Nadia** (female, ar-001): A low, warm Arabic woman in her early forties speaking clear Modern Standard Arabic. She explains legal, financial and policy topics with calm, trustworthy care. Sample: https://cdn.scenema.ai/public/content/voice/nadia/sample-pro-v2.mp3 - **Nour** (female, ar-001): A professional yet approachable woman speaking polished Modern Standard Arabic. Built for legal, government and corporate content across the whole Arab region. Sample: https://cdn.scenema.ai/public/content/voice/nour/sample-pro-v2.mp3 - **Omar** (male, ar-001): A low, confident Arabic man in his late forties speaking clear Modern Standard Arabic. He walks viewers through lessons and product ideas at an easy, relaxed pace. Sample: https://cdn.scenema.ai/public/content/voice/omar/sample-pro-v2.mp3 - **Rania** (female, ar-001): A young woman with a textured, resonant and soothing voice in Modern Standard Arabic. Suited to character roles, dramatic stories and stylish brand moments. Sample: https://cdn.scenema.ai/public/content/voice/rania/sample-pro-v2.mp3 - **Sherif** (male, ar-001): A low, crisp Arabic man in his early fifties speaking clear Modern Standard Arabic. He hosts training and instructional videos with eager, authoritative energy. Sample: https://cdn.scenema.ai/public/content/voice/sherif/sample-pro-v2.mp3 - **Tariq** (male, ar-001): A low, assured Arabic man in his early thirties speaking clear Modern Standard Arabic. He presents software, platforms and technical ideas with focused authority. Sample: https://cdn.scenema.ai/public/content/voice/tariq/sample-pro-v2.mp3 - **Walid** (male, ar-001): A resonant, witty male teacher in Modern Standard Arabic. Built for lessons, science and history explainers that should stay engaging. Sample: https://cdn.scenema.ai/public/content/voice/walid/sample-pro-v2.mp3 - **Habiba** (female, ar-EG): A warm, engaging young woman speaking natural Egyptian Arabic. Perfect for friendly stories, family content and casual explainers. Sample: https://cdn.scenema.ai/public/content/voice/habiba/sample-pro-v2.mp3 - **Hassan** (male, ar-EG): A mature, low male voice that sounds confident and clear in Egyptian Arabic. Ideal for interviews, commentary and conversational explainers with real character. Sample: https://cdn.scenema.ai/public/content/voice/hassan/sample-pro-v2.mp3 - **Mahmoud** (male, ar-EG): A warm, engaging man in his late forties with a low Egyptian Arabic voice. Great for heartfelt stories, wellness talks and conversational explainers. Sample: https://cdn.scenema.ai/public/content/voice/mahmoud/sample-pro-v2.mp3 - **Salma** (female, ar-EG): An objective, direct female voice in natural Egyptian Arabic. Made for documentaries, science explainers and helpful informational videos across the Arab world. Sample: https://cdn.scenema.ai/public/content/voice/salma/sample-pro-v2.mp3 - **Samia** (female, ar-EG): An energetic, colorful and fast woman in her sixties with big Egyptian charm. Great for lively ads, retail promos and fun brand spots. Sample: https://cdn.scenema.ai/public/content/voice/samia/sample-pro-v2.mp3 - **Youssef** (male, ar-EG): A young male voice in Egyptian Arabic that is objective, direct and helpful. Suited to product reviews, tech ads and straight talking social spots. Sample: https://cdn.scenema.ai/public/content/voice/youssef/sample-pro-v2.mp3 ### French (20 voices) - **Benoit** (male, fr-CA): A low, steady Montreal man in his late forties with a journalist's professional yet approachable tone. Suits Quebec news explainers, podcasts and data stories. Sample: https://cdn.scenema.ai/public/content/voice/benoit/sample-pro-v2.mp3 - **Catherine** (female, fr-CA): A bright, confident Montreal woman in her late thirties with a chatty, stylish delivery. Great for Quebec brand stories, lifestyle content and retail promos. Sample: https://cdn.scenema.ai/public/content/voice/catherine/sample-pro-v2.mp3 - **Étienne** (male, fr-CA): A mature, low male voice that sounds confident and clear in Montreal French. Made for lessons, training and documentary style explainers for Quebec. Sample: https://cdn.scenema.ai/public/content/voice/etienne/sample-pro-v2.mp3 - **Gabriel** (male, fr-CA): A young man with a low, intimate Montreal French voice. Suited to fintech, banking and advice content for younger Quebec audiences. Sample: https://cdn.scenema.ai/public/content/voice/gabriel/sample-pro-v2.mp3 - **Genevieve** (female, fr-CA): A low, intimate female voice in Montreal French with a talk show warmth. Built for financial advice, banking and insurance videos in Quebec. Sample: https://cdn.scenema.ai/public/content/voice/genevieve/sample-pro-v2.mp3 - **Jean Philippe** (male, fr-CA): A warm, engaging young man in Montreal French. Great for cooking, how to and training videos aimed at Quebec viewers. Sample: https://cdn.scenema.ai/public/content/voice/jean-philippe/sample-pro-v2.mp3 - **Josiane** (female, fr-CA): A bright woman with an intimate, talk show warmth in Montreal French. Made for cooking, lifestyle and onboarding videos for Quebec viewers. Sample: https://cdn.scenema.ai/public/content/voice/josiane/sample-pro-v2.mp3 - **Marianne** (female, fr-CA): An engaging, empathic young woman in Montreal French with a coach's encouragement. Great for wellness, motivation and personal growth videos. Sample: https://cdn.scenema.ai/public/content/voice/marianne/sample-pro-v2.mp3 - **Alain** (male, fr-FR): A warm, low Parisian man in his early sixties with a conversational tone and a touch of dry humor. Ideal for French lessons, history explainers and video essays. Sample: https://cdn.scenema.ai/public/content/voice/alain/sample-pro-v2.mp3 - **Aminata** (female, fr-FR): A light, airy and precise young woman speaking Paris French. Made for lessons, SaaS explainers and onboarding videos that need clarity. Sample: https://cdn.scenema.ai/public/content/voice/aminata/sample-pro-v2.mp3 - **Hélène** (female, fr-FR): A deep, velvety Parisian woman in her mid fifties with an unhurried delivery. Made for French wellness, fitness and mindful brand storytelling. Sample: https://cdn.scenema.ai/public/content/voice/helene/sample-pro-v2.mp3 - **Isabelle** (female, fr-FR): A warm, engaging woman in her forties with a low Paris French voice. Made for food, lifestyle and brand commercials with a welcoming touch. Sample: https://cdn.scenema.ai/public/content/voice/isabelle/sample-pro-v2.mp3 - **Josephine** (female, fr-FR): A confident, clear Parisian woman in her mid forties with a relatable, parental warmth. Good for French onboarding, help content and family explainers. Sample: https://cdn.scenema.ai/public/content/voice/josephine/sample-pro-v2.mp3 - **Lan** (female, fr-FR): An energetic, colorful and fast young woman speaking Paris French. Great for lively stories, social content and playful brand videos. Sample: https://cdn.scenema.ai/public/content/voice/lan/sample-pro-v2.mp3 - **Mathieu** (male, fr-FR): A fast, articulate Parisian professor in his early fifties with real energy. Built for French lectures, science explainers and sharp B2B presentations. Sample: https://cdn.scenema.ai/public/content/voice/mathieu/sample-pro-v2.mp3 - **Mehdi** (male, fr-FR): A low, confident and clear male voice in Paris French. Built for SaaS explainers, lessons and B2B overviews where clarity matters most. Sample: https://cdn.scenema.ai/public/content/voice/mehdi/sample-pro-v2.mp3 - **Moussa** (male, fr-FR): A crisp, eager young man in Paris French. Built for upbeat ads, product launches and support videos that need energy and clarity. Sample: https://cdn.scenema.ai/public/content/voice/moussa/sample-pro-v2.mp3 - **Philippe** (male, fr-FR): A low, natural Parisian man in his mid fifties with the easy clarity of a podcast interviewer. Fits French podcasts, video essays and long form explainers. Sample: https://cdn.scenema.ai/public/content/voice/philippe/sample-pro-v2.mp3 - **Thierry** (male, fr-FR): A laid back, encouraging male voice with a chill Paris radio style. Ideal for podcasts, video essays and relaxed explainers. Sample: https://cdn.scenema.ai/public/content/voice/thierry/sample-pro-v2.mp3 - **Yasmine** (female, fr-FR): A confident Parisian woman in her early thirties with a clear, precise delivery. Built for legal explainers, compliance modules and B2B overviews in French. Sample: https://cdn.scenema.ai/public/content/voice/yasmine/sample-pro-v2.mp3 ### Portuguese (20 voices) - **Beatriz** (female, pt-BR): A light, airy and precise Brazilian woman of sixty with a calm documentary style. Ideal for nature films, science stories and gentle brand narratives. Sample: https://cdn.scenema.ai/public/content/voice/beatriz/sample-pro-v2.mp3 - **Bruna** (female, pt-BR): A warm, engaging Brazilian woman in her early thirties with a lawyer's assurance and a bright tone. Ideal for rights explainers, fintech and B2B content. Sample: https://cdn.scenema.ai/public/content/voice/bruna/sample-pro-v2.mp3 - **Caio** (male, pt-BR): A warm, engaging Brazilian man in his mid thirties with a low, thoughtful writing tutor's tone. Great for courses, video essays and creative lessons. Sample: https://cdn.scenema.ai/public/content/voice/caio/sample-pro-v2.mp3 - **Heitor** (male, pt-BR): A cool, confident Brazilian man in his mid forties with a low, collaborative tone. Fits podcasts, tech commentary and B2B storytelling in Portuguese. Sample: https://cdn.scenema.ai/public/content/voice/heitor/sample-pro-v2.mp3 - **Kenji** (male, pt-BR): A low, confident Brazilian man in his mid fifties with a clear, caring tone. Built for trustworthy ads, nonprofit appeals and public service campaigns. Sample: https://cdn.scenema.ai/public/content/voice/kenji/sample-pro-v2.mp3 - **Larissa** (female, pt-BR): A warm, engaging Brazilian professor in her early sixties with a bright, caring voice. Made for lessons, history and culture content and patient education. Sample: https://cdn.scenema.ai/public/content/voice/larissa/sample-pro-v2.mp3 - **Mariana** (female, pt-BR): A bright, youthful Brazilian woman in her early twenties with an influencer's polish. Made for social ads, app launches and e-commerce promos in Brazil. Sample: https://cdn.scenema.ai/public/content/voice/mariana/sample-pro-v2.mp3 - **Murilo** (male, pt-BR): A professional yet approachable Brazilian teacher in his late thirties with a calm, medium tone. Ideal for courses, science lessons and SaaS explainers. Sample: https://cdn.scenema.ai/public/content/voice/murilo/sample-pro-v2.mp3 - **Patricia** (female, pt-BR): A bright, breezy and youthful Brazilian woman in her mid thirties with a radio host's ease. Great for podcasts, lifestyle content and upbeat brand spots. Sample: https://cdn.scenema.ai/public/content/voice/patricia/sample-pro-v2.mp3 - **Reinaldo** (male, pt-BR): A low, confident Brazilian tutor in his mid fifties with a clear, patient delivery. Suits technical training, lessons and step by step walkthroughs. Sample: https://cdn.scenema.ai/public/content/voice/reinaldo/sample-pro-v2.mp3 - **Renata** (female, pt-BR): A warm, engaging Brazilian woman of fifty with a calm documentary delivery. Ideal for nature films, sustainability stories and science explainers in Portuguese. Sample: https://cdn.scenema.ai/public/content/voice/renata/sample-pro-v2.mp3 - **Thiago** (male, pt-BR): A relaxed, low Brazilian man in his mid thirties with a financial advisor's steady assurance. Ideal for money, fintech and insurance explainers. Sample: https://cdn.scenema.ai/public/content/voice/thiago/sample-pro-v2.mp3 - **Vanessa** (female, pt-BR): A bright Brazilian woman in her late twenties with a professional yet approachable radio tone. Great for app explainers, news recaps and onboarding. Sample: https://cdn.scenema.ai/public/content/voice/vanessa/sample-pro-v2.mp3 - **Wagner** (male, pt-BR): A low, engaging Brazilian man in his late forties with a comedian's timing and empathy. Great for entertaining explainers, podcasts and character driven stories. Sample: https://cdn.scenema.ai/public/content/voice/wagner/sample-pro-v2.mp3 - **Duarte** (male, pt-PT): A natural, clear European Portuguese man in his early thirties with a low, steady tone. Built for software tutorials, onboarding and training videos for Portugal. Sample: https://cdn.scenema.ai/public/content/voice/duarte/sample-pro-v2.mp3 - **Leonor** (female, pt-PT): A bright European Portuguese woman in her mid forties with an objective, direct and helpful tone. Fits trivia, explainers and support content for Portugal. Sample: https://cdn.scenema.ai/public/content/voice/leonor/sample-pro-v2.mp3 - **Madalena** (female, pt-PT): A fast, articulate European Portuguese woman in her mid forties with a lawyer's precision. Suits legal, financial and compliance content for Portugal. Sample: https://cdn.scenema.ai/public/content/voice/madalena/sample-pro-v2.mp3 - **Matilde** (female, pt-PT): A warm, engaging European Portuguese woman of thirty with a cooking show host's friendliness. Ideal for how to guides, food content and onboarding in Portugal. Sample: https://cdn.scenema.ai/public/content/voice/matilde/sample-pro-v2.mp3 - **Nelson** (male, pt-PT): A low, natural European Portuguese man in his early thirties with a composed advisor tone. Suits corporate, legal and financial explainers in Portugal. Sample: https://cdn.scenema.ai/public/content/voice/nelson/sample-pro-v2.mp3 - **Rui** (male, pt-PT): A low, patient European Portuguese man in his mid forties with a chess instructor's careful logic. Suits lessons, strategy explainers and training in Portugal. Sample: https://cdn.scenema.ai/public/content/voice/rui/sample-pro-v2.mp3 ### German (17 voices) - **Bastian** (male, de): A warm, engaging man of thirty with a low, friendly instructional tone in standard German. Great for tutorials, onboarding and how to videos. Sample: https://cdn.scenema.ai/public/content/voice/bastian/sample-pro-v2.mp3 - **Annika** (female, de-DE): An engaging, empathic German woman in her mid twenties with a youthful teaching voice. Ideal for courses, science explainers and student focused content. Sample: https://cdn.scenema.ai/public/content/voice/annika/sample-pro-v2.mp3 - **Birgit** (female, de-DE): A crisp, eager German woman of fifty with a low, assured tone. Built for commercials, product launches and confident brand promos. Sample: https://cdn.scenema.ai/public/content/voice/birgit/sample-pro-v2.mp3 - **Carina** (female, de-DE): A clear, confident German woman of sixty with a natural storyteller's warmth. Great for documentaries, brand stories and family friendly narration. Sample: https://cdn.scenema.ai/public/content/voice/carina/sample-pro-v2.mp3 - **Fabian** (male, de-DE): A low, confident German researcher in his late thirties with a clear, measured delivery. Built for science, data and technical B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/fabian/sample-pro-v2.mp3 - **Franziska** (female, de-DE): A light, airy and precise German woman of forty with a doctor's clarity. Made for patient education, pharma and medical explainers. Sample: https://cdn.scenema.ai/public/content/voice/franziska/sample-pro-v2.mp3 - **Heidi** (female, de-DE): A relaxed German woman in her mid thirties with a calm academic tone. Ideal for lessons, SaaS explainers and help center content. Sample: https://cdn.scenema.ai/public/content/voice/heidi/sample-pro-v2.mp3 - **Heike** (female, de-DE): A cool, confident German woman in her early forties with a bright, collaborative host tone. Fits podcasts, listicles and lively explainers. Sample: https://cdn.scenema.ai/public/content/voice/heike/sample-pro-v2.mp3 - **Hendrik** (male, de-DE): A low German man in his mid fifties with a peer to peer, curious cooking show tone. Suits how to guides, food content and friendly training. Sample: https://cdn.scenema.ai/public/content/voice/hendrik/sample-pro-v2.mp3 - **Johanna** (female, de-DE): A natural, clear German woman in her mid thirties with a low, grounded tone. Built for credible commercials, public campaigns and nonprofit appeals. Sample: https://cdn.scenema.ai/public/content/voice/johanna/sample-pro-v2.mp3 - **Josef** (male, de-DE): An enthusiastic, fun German fitness trainer in his early thirties with a low, punchy voice. Great for workout content, energetic promos and character spots. Sample: https://cdn.scenema.ai/public/content/voice/josef/sample-pro-v2.mp3 - **Kilian** (male, de-DE): A warm, engaging German man of thirty with a low, assured lawyer's tone. Ideal for legal, compliance and B2B explainers in German. Sample: https://cdn.scenema.ai/public/content/voice/kilian/sample-pro-v2.mp3 - **Matthias** (male, de-DE): A low German man in his early fifties with a professional yet approachable storytelling tone. Suits company films, brand stories and long form explainers. Sample: https://cdn.scenema.ai/public/content/voice/matthias/sample-pro-v2.mp3 - **Reinhard** (male, de-DE): A reflective, calm German man in his late fifties with a reassuring, thoughtful voice. Made for video essays, history and contemplative brand films. Sample: https://cdn.scenema.ai/public/content/voice/reinhard/sample-pro-v2.mp3 - **Sabine** (female, de-DE): A relaxed German woman in her early forties with a therapist's calm, caring tone. Made for wellness, mental health and patient friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/sabine/sample-pro-v2.mp3 - **Steffi** (female, de-DE): A warm, engaging German woman in her late thirties with a therapist's supportive tone. Great for coaching, HR training and wellbeing content. Sample: https://cdn.scenema.ai/public/content/voice/steffi/sample-pro-v2.mp3 - **Tobias** (male, de-DE): A low German man in his late fifties with an objective, direct documentary voice. Ideal for nature films, science documentaries and history. Sample: https://cdn.scenema.ai/public/content/voice/tobias/sample-pro-v2.mp3 ### Japanese (16 voices) - **Aoi** (female, ja-JP): A young female Japanese voice from Fukuoka with a warm, comforting tone. Made for gentle stories, personal brand films and friendly creator narration. Sample: https://cdn.scenema.ai/public/content/voice/aoi/sample-pro-v2.mp3 - **Asuka** (female, ja-JP): A warm Tokyo woman in her early forties with a conversational tone and a touch of dry humor. Ideal for lessons, culture explainers and help content. Sample: https://cdn.scenema.ai/public/content/voice/asuka/sample-pro-v2.mp3 - **Ayumi** (female, ja-JP): A low, confident Tokyo Japanese female voice with the clarity of a physician. Ideal for patient education, healthcare and trusted advisory content. Sample: https://cdn.scenema.ai/public/content/voice/ayumi/sample-pro-v2.mp3 - **Haruto** (male, ja-JP): A low, seasoned Tokyo Japanese male voice that talks with energy, color and speed. Great for podcasts, commentary and engaging current affairs videos. Sample: https://cdn.scenema.ai/public/content/voice/haruto/sample-pro-v2.mp3 - **Hina** (female, ja-JP): A young Japanese woman in her early twenties with an unexpectedly deep, velvety and unhurried voice. Made for stylish ads, beauty and lifestyle brands. Sample: https://cdn.scenema.ai/public/content/voice/hina/sample-pro-v2.mp3 - **Hiroshi** (male, ja-JP): A clear, friendly Tokyo man in his early sixties with a steady instructional tone. Ideal for tutorials, technical training and onboarding. Sample: https://cdn.scenema.ai/public/content/voice/hiroshi/sample-pro-v2.mp3 - **Keiko** (female, ja-JP): A mature Tokyo Japanese female voice with a measured, approachable tone. Ideal for nature documentaries, science explainers and educational films. Sample: https://cdn.scenema.ai/public/content/voice/keiko/sample-pro-v2.mp3 - **Kenta** (male, ja-JP): A mid range Japanese male host voice from Fukuoka, warm and conversational with a hint of dry humor. Ideal for tutorials, how to videos and training. Sample: https://cdn.scenema.ai/public/content/voice/kenta/sample-pro-v2.mp3 - **Masato** (male, ja-JP): A low, reflective Tokyo Japanese male voice with the thoughtful pacing of a philosopher. Great for video essays, history and ideas driven explainers. Sample: https://cdn.scenema.ai/public/content/voice/masato/sample-pro-v2.mp3 - **Megumi** (female, ja-JP): A mature female Japanese voice from Fukuoka, low and measured, with the steady ease of an experienced teacher. Good for lessons, onboarding and clear explainers. Sample: https://cdn.scenema.ai/public/content/voice/megumi/sample-pro-v2.mp3 - **Naoko** (female, ja-JP): A higher pitched Japanese female voice from Fukuoka with a calm, reflective warmth. Suits considered product ads, design and real estate promos. Sample: https://cdn.scenema.ai/public/content/voice/naoko/sample-pro-v2.mp3 - **Ren** (male, ja-JP): A young, low Tokyo Japanese male voice with a composed, professorial delivery. Fits university style lessons, tech explainers and study channels. Sample: https://cdn.scenema.ai/public/content/voice/ren/sample-pro-v2.mp3 - **Satoshi** (male, ja-JP): A textured, resonant Japanese man in his late fifties with a soothing, authoritative tone. Built for science documentaries, research and premium brand films. Sample: https://cdn.scenema.ai/public/content/voice/satoshi/sample-pro-v2.mp3 - **Sota** (male, ja-JP): A young male Japanese voice from Osaka with a soft, low tone that comforts and encourages. Suited to wellness videos, mindfulness guides and supportive coaching content. Sample: https://cdn.scenema.ai/public/content/voice/sota/sample-pro-v2.mp3 - **Takeshi** (male, ja-JP): A low, relaxed Japanese male voice from Osaka with the composed authority of a legal advisor. Builds trust in finance, legal and B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/takeshi/sample-pro-v2.mp3 - **Yui** (female, ja-JP): A bright, confident Tokyo woman in her late twenties with a clear interviewer's delivery. Great for podcasts, app explainers and news recaps. Sample: https://cdn.scenema.ai/public/content/voice/yui/sample-pro-v2.mp3 ### Korean (16 voices) - **Chaewon** (female, ko-KR): A bright, high pitched young Seoul Korean female voice with a laid back, encouraging vibe. Perfect for fashion, beauty and social ads. Sample: https://cdn.scenema.ai/public/content/voice/chaewon/sample-pro-v2.mp3 - **Dahyun** (female, ko-KR): A bright young Korean female voice from Busan with a peer to peer, curious tone. Great for social ads, product reviews and creator content. Sample: https://cdn.scenema.ai/public/content/voice/dahyun/sample-pro-v2.mp3 - **Donghyun** (male, ko-KR): A low, confident Seoul Korean male voice with the easy rhythm of a podcast interviewer. Great for podcasts, commentary and conversational explainers. Sample: https://cdn.scenema.ai/public/content/voice/donghyun/sample-pro-v2.mp3 - **Eunji** (female, ko-KR): A higher pitched Seoul Korean female voice that is fast paced, articulate and energetic. Strong for commentary, explainers and engaging stories. Sample: https://cdn.scenema.ai/public/content/voice/eunji/sample-pro-v2.mp3 - **Hyejin** (female, ko-KR): A textured, resonant Seoul Korean female voice with soothing authority. Ideal for architecture, tech, B2B and premium brand explainers. Sample: https://cdn.scenema.ai/public/content/voice/hyejin/sample-pro-v2.mp3 - **Hyunwoo** (male, ko-KR): A low, relaxed Seoul Korean male host voice with an easy, friendly manner. Perfect for cooking, food brands and laid back how to videos. Sample: https://cdn.scenema.ai/public/content/voice/hyunwoo/sample-pro-v2.mp3 - **Jaewon** (male, ko-KR): A low Seoul Korean male voice that is crisp and eager like a dedicated tutor. Strong for lessons, exam prep and software explainers. Sample: https://cdn.scenema.ai/public/content/voice/jaewon/sample-pro-v2.mp3 - **Jihoon** (male, ko-KR): A low Seoul Korean male voice with warm, engaging authority. Ideal for legal, financial and enterprise explainers that need trust without stiffness. Sample: https://cdn.scenema.ai/public/content/voice/jihoon/sample-pro-v2.mp3 - **Kyungsoo** (male, ko-KR): A low, warm Seoul Korean male voice with the authority of a veteran journalist. Ideal for news explainers, documentaries and analysis. Sample: https://cdn.scenema.ai/public/content/voice/kyungsoo/sample-pro-v2.mp3 - **Minji** (female, ko-KR): A young Seoul Korean female voice, low in pitch yet bright, breezy and youthful. Great for app explainers, lifestyle content and friendly creator videos. Sample: https://cdn.scenema.ai/public/content/voice/minji/sample-pro-v2.mp3 - **Seojun** (male, ko-KR): A young, low Korean male voice from Busan with a professional yet approachable tone. Suited to lessons, study content and calm explainers. Sample: https://cdn.scenema.ai/public/content/voice/seojun/sample-pro-v2.mp3 - **Seoyeon** (female, ko-KR): A bright, young Seoul Korean female voice with a textured, soothing tone. Lovely for nature films, wellness and gentle documentary storytelling. Sample: https://cdn.scenema.ai/public/content/voice/seoyeon/sample-pro-v2.mp3 - **Soyeon** (female, ko-KR): A medium pitched Seoul Korean female voice, crisp and eager like an enthusiastic teacher. Great for lessons, creative courses and kids learning. Sample: https://cdn.scenema.ai/public/content/voice/soyeon/sample-pro-v2.mp3 - **Sungmin** (male, ko-KR): A mid range Seoul Korean male host voice that sounds confident and clear. Built for tutorials, onboarding and internal training videos. Sample: https://cdn.scenema.ai/public/content/voice/sungmin/sample-pro-v2.mp3 - **Yoona** (female, ko-KR): A higher pitched senior Seoul Korean female voice, warm and conversational with gentle dry humor. Lovely for nature films, heritage stories and family content. Sample: https://cdn.scenema.ai/public/content/voice/yoona/sample-pro-v2.mp3 - **Youngho** (male, ko-KR): A low, mature Seoul Korean male voice with a crisp, eager delivery. Good for nutrition, fitness and healthy living coaching videos. Sample: https://cdn.scenema.ai/public/content/voice/youngho/sample-pro-v2.mp3 ### Italian (12 voices) - **Aurora** (female, it): A bright, young female voice in standard Italian with a professional yet approachable tone. Built for social ads, ecommerce and indie brand promos. Sample: https://cdn.scenema.ai/public/content/voice/aurora/sample-pro-v2.mp3 - **Chiara** (female, it): A medium pitched young female voice in standard Italian, laid back and encouraging. Fits nature films, travel stories and gentle documentaries. Sample: https://cdn.scenema.ai/public/content/voice/chiara/sample-pro-v2.mp3 - **Fabrizio** (male, it): A firm, direct and commanding male voice in standard Italian with a lower pitch. Made for authoritative instructions, announcements and corporate content. Sample: https://cdn.scenema.ai/public/content/voice/fabrizio/sample-pro-v2.mp3 - **Graziella** (female, it): A bright, senior female voice in standard Italian with a confident, reflective manner. Lovely for essays, history, culture and thoughtful storytelling. Sample: https://cdn.scenema.ai/public/content/voice/graziella/sample-pro-v2.mp3 - **Gianni** (male, it-IT): A low Italian male voice with laid back, encouraging authority. Fits legal, finance and B2B explainers that should feel approachable. Sample: https://cdn.scenema.ai/public/content/voice/gianni/sample-pro-v2.mp3 - **Giulia** (female, it-IT): A bright, higher pitched young Italian female voice that sounds confident and clear. Good for lessons, app explainers and study content. Sample: https://cdn.scenema.ai/public/content/voice/giulia/sample-pro-v2.mp3 - **Lorenzo** (male, it-IT): A low, warm Italian male host voice with a radio quality. Perfect for cooking, food brands and friendly tutorial videos. Sample: https://cdn.scenema.ai/public/content/voice/lorenzo/sample-pro-v2.mp3 - **Massimo** (male, it-IT): A higher pitched, warm and engaging senior Italian male voice. A distinctive coach for fitness, healthy aging and motivational content. Sample: https://cdn.scenema.ai/public/content/voice/massimo/sample-pro-v2.mp3 - **Orietta** (female, it-IT): A low Italian female voice with an intimate, talk show warmth. Great for podcasts, personal stories and conversational explainers. Sample: https://cdn.scenema.ai/public/content/voice/orietta/sample-pro-v2.mp3 - **Raffaella** (female, it-IT): A cool, confident Italian woman in her forties with a bright, collaborative tone. She guides learners through tutorials, courses and onboarding as if working right beside them. Sample: https://cdn.scenema.ai/public/content/voice/raffaella/sample-pro-v2.mp3 - **Stefano** (male, it-IT): A low, mature Italian male voice with the patience of a chess instructor and a broadcast polish. Ideal for lessons, strategy and analysis. Sample: https://cdn.scenema.ai/public/content/voice/stefano/sample-pro-v2.mp3 - **Tommaso** (male, it-IT): A low, young Italian male voice that is cool, confident and collaborative. Great for software tutorials, onboarding and modern training. Sample: https://cdn.scenema.ai/public/content/voice/tommaso/sample-pro-v2.mp3 ### Amharic (4 voices) - **Dawit** (male, am): A low, steady male voice with the calm assurance of a seasoned legal advisor. Suited to Amharic compliance training, financial guidance and B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/dawit/sample-pro-v2.mp3 - **Hiwot** (female, am): A light, airy female voice with precise diction and an easy storytelling flow. Good for Amharic brand stories, explainer videos and friendly YouTube narration. Sample: https://cdn.scenema.ai/public/content/voice/hiwot/sample-pro-v2.mp3 - **Selam** (female, am): An engaging, empathic female voice in her late twenties for Amharic nature documentaries, climate and nonprofit films. Bright and gentle, she brings wonder to the story. Sample: https://cdn.scenema.ai/public/content/voice/selam/sample-pro-v2.mp3 - **Yonas** (male, am): A young male voice with a relaxed influencer ease that still lands a call to action. Built for Amharic social ads, product launches and ecommerce promos. Sample: https://cdn.scenema.ai/public/content/voice/yonas/sample-pro-v2.mp3 ### Bengali (4 voices) - **Arnab** (male, bn): A smooth, confident male voice in his early fifties for Bengali brand ads, retail campaigns and company films. Cool and polished, he suits premium brands. Sample: https://cdn.scenema.ai/public/content/voice/arnab/sample-pro-v2.mp3 - **Nusrat** (female, bn): A warm, engaging female voice in her mid twenties for Bengali lessons, children's learning and public health videos. She teaches with warmth and patience. Sample: https://cdn.scenema.ai/public/content/voice/nusrat/sample-pro-v2.mp3 - **Tasnim** (female, bn): A cool, confident female voice in her early twenties for Bengali app explainers, YouTube channels and tech content. Collaborative and composed, she sounds modern. Sample: https://cdn.scenema.ai/public/content/voice/tasnim/sample-pro-v2.mp3 - **Yash** (male, bn): An energetic, persuasive male voice in his early forties for Bengali legal, finance and sales content. Fast and colorful, he makes expert advice lively. Sample: https://cdn.scenema.ai/public/content/voice/yash/sample-pro-v2.mp3 ### Cantonese (4 voices) - **Chun Kit** (male, yue): A young male voice with a resonant low tone and a quick, witty edge. Great for Cantonese fashion, lifestyle and ecommerce ads that need personality. Sample: https://cdn.scenema.ai/public/content/voice/chun-kit/sample-pro-v2.mp3 - **Hoi Ying** (female, yue): A gentle, approachable female voice with the patience of a counselor. Made for Cantonese wellness content, patient education and supportive onboarding. Sample: https://cdn.scenema.ai/public/content/voice/hoi-ying/sample-pro-v2.mp3 - **Ka Ho** (male, yue): A low, approachable male voice with a journalist's clarity and credibility. Fits Cantonese news explainers, current affairs and corporate reports. Sample: https://cdn.scenema.ai/public/content/voice/ka-ho/sample-pro-v2.mp3 - **Wing Yan** (female, yue): A bright, precise female voice with a trivia host's knack for making facts land. Suits Cantonese science explainers, lessons and fun fact videos. Sample: https://cdn.scenema.ai/public/content/voice/wing-yan/sample-pro-v2.mp3 ### Dutch (4 voices) - **Jayden** (male, nl-NL): A young Dutch man with a clear, friendly voice and a grounded low register. He explains research, tech and business topics in a direct way that feels credible and easy to trust. Sample: https://cdn.scenema.ai/public/content/voice/jayden/sample-pro-v2.mp3 - **Katrien** (female, nl-NL): A senior Dutch female voice that stays bright, breezy and youthful. Lovely for stories, brand films and warm conversational narration. Sample: https://cdn.scenema.ai/public/content/voice/katrien/sample-pro-v2.mp3 - **Lennart** (male, nl-NL): A low Dutch male voice that is confident and clear with relaxed authority. Fits legal, finance, compliance and B2B explainers. Sample: https://cdn.scenema.ai/public/content/voice/lennart/sample-pro-v2.mp3 - **Lore** (female, nl-NL): A bright Dutch female voice with an objective, direct and helpful tone. Ideal for SaaS explainers, onboarding and lessons. Sample: https://cdn.scenema.ai/public/content/voice/lore/sample-pro-v2.mp3 ### Filipino (4 voices) - **Paolo** (male, fil): An approachable, upbeat male voice in his mid twenties for Filipino social ads, telecom and app promos. Professional and friendly, he connects with young buyers. Sample: https://cdn.scenema.ai/public/content/voice/paolo/sample-pro-v2.mp3 - **Ramon** (male, fil): A confident, clear male voice in his early forties for Filipino legal, compliance and B2B content. Low and steady, he gives policy material real weight. Sample: https://cdn.scenema.ai/public/content/voice/ramon/sample-pro-v2.mp3 - **Rosario** (female, fil): A clear, friendly female voice in her late fifties for Filipino lessons, kids learning and how to guides. Patient and warm, she teaches like a beloved tita. Sample: https://cdn.scenema.ai/public/content/voice/rosario/sample-pro-v2.mp3 - **Tala** (female, fil): A clear, friendly female voice in her mid twenties for Filipino podcasts, YouTube and app explainers. Cheerful and bright, she sounds like a favorite radio DJ. Sample: https://cdn.scenema.ai/public/content/voice/tala/sample-pro-v2.mp3 ### Hebrew (4 voices) - **Itai** (male, he): A resonant, witty male voice in his late twenties for Hebrew ads, trailers and ecommerce promos. Confident and playful, he gives brands personality. Sample: https://cdn.scenema.ai/public/content/voice/itai/sample-pro-v2.mp3 - **Noa** (female, he): A warm, engaging female voice in her mid thirties for Hebrew podcasts, commentary and news style content. She has the friendly ease of a radio presenter. Sample: https://cdn.scenema.ai/public/content/voice/noa/sample-pro-v2.mp3 - **Oren** (male, he): A seasoned, professional male voice around fifty for Hebrew corporate films, B2B overviews and compliance training. Approachable and assured, he suits enterprise brands. Sample: https://cdn.scenema.ai/public/content/voice/oren/sample-pro-v2.mp3 - **Yael** (female, he): An empathic, reflective female voice in her late forties for Hebrew documentaries, wellness and nonprofit films. Gentle and engaging, she connects on a human level. Sample: https://cdn.scenema.ai/public/content/voice/yael/sample-pro-v2.mp3 ### Indonesian (4 voices) - **Budi** (male, id): An assured male voice in his early forties for Indonesian legal, finance and corporate videos. His low register carries a surprisingly light, breezy warmth. Sample: https://cdn.scenema.ai/public/content/voice/budi/sample-pro-v2.mp3 - **Hendra** (male, id): A crisp, eager male voice in his mid fifties for Indonesian commercials, retail promos and product launches. Seasoned and polished, he sells with style. Sample: https://cdn.scenema.ai/public/content/voice/hendra/sample-pro-v2.mp3 - **Putri** (female, id): A bright, clear female voice in her early twenties for Indonesian lessons, science explainers and study apps. Confident and fresh, she suits young learners. Sample: https://cdn.scenema.ai/public/content/voice/putri/sample-pro-v2.mp3 - **Sekar** (female, id): A warm, engaging female voice in her late twenties for Indonesian brand stories, short films and narrative YouTube. She draws listeners in with a cinematic touch. Sample: https://cdn.scenema.ai/public/content/voice/sekar/sample-pro-v2.mp3 ### Marathi (4 voices) - **Omkar** (male, mr): An energetic, approachable male voice in his early twenties for Marathi ads, startup pitches and launch videos. Fresh and credible, he speaks to young audiences. Sample: https://cdn.scenema.ai/public/content/voice/omkar/sample-pro-v2.mp3 - **Sayali** (female, mr): A confident, clear female voice in her late twenties for Marathi podcasts, news explainers and YouTube. She has the easy polish of a radio presenter. Sample: https://cdn.scenema.ai/public/content/voice/sayali/sample-pro-v2.mp3 - **Sunanda** (female, mr): A crisp, eager female voice in her early sixties for Marathi documentaries, history and lessons. Wise and lively, she brings decades of perspective. Sample: https://cdn.scenema.ai/public/content/voice/sunanda/sample-pro-v2.mp3 - **Vinayak** (male, mr): A grounded, approachable male voice in his late forties for Marathi legal, civic and compliance content. Professional and steady, he explains rules plainly. Sample: https://cdn.scenema.ai/public/content/voice/vinayak/sample-pro-v2.mp3 ### Persian (4 voices) - **Farhad** (male, fa): A breezy, youthful sounding male voice in his early fifties for Persian retail ads, promos and event trailers. Bright and fun, he keeps ads light. Sample: https://cdn.scenema.ai/public/content/voice/farhad/sample-pro-v2.mp3 - **Kaveh** (male, fa): A relaxed, authoritative male voice in his mid thirties for Persian legal, finance and corporate videos. Unhurried and assured, he earns trust quickly. Sample: https://cdn.scenema.ai/public/content/voice/kaveh/sample-pro-v2.mp3 - **Parisa** (female, fa): A bright, warm female voice in her mid twenties for Persian onboarding, app explainers and help content. Friendly and chatty, she feels like a helpful friend. Sample: https://cdn.scenema.ai/public/content/voice/parisa/sample-pro-v2.mp3 - **Shirin** (female, fa): A warm, thoughtful female voice in her mid twenties for Persian video essays, short fiction and history. She reads like a curious mind in a quiet bookshop. Sample: https://cdn.scenema.ai/public/content/voice/shirin/sample-pro-v2.mp3 ### Polish (4 voices) - **Szymon** (male, pl): A bright, senior male voice in standard Polish with a professional yet approachable tone. Suits trusted product ads and reassuring brand spots. Sample: https://cdn.scenema.ai/public/content/voice/szymon/sample-pro-v2.mp3 - **Agnieszka** (female, pl-PL): A medium pitched Polish female voice that is cool, confident and collaborative. Great for podcasts, quizzes and engaging explainers. Sample: https://cdn.scenema.ai/public/content/voice/agnieszka/sample-pro-v2.mp3 - **Claire** (female, pl-PL): A low, young Polish female voice with a calm, comforting tone. Good for lessons, wellness topics and patient explainers. Sample: https://cdn.scenema.ai/public/content/voice/claire/sample-pro-v2.mp3 - **Wojciech** (male, pl-PL): A low, composed Polish male voice with professional yet approachable authority. Fits legal, finance and enterprise explainers. Sample: https://cdn.scenema.ai/public/content/voice/wojciech/sample-pro-v2.mp3 ### Swahili (4 voices) - **Juma** (male, sw): A young male voice in Swahili with a low, calm and reassuring tone. Suited to brand ads, app promos and soft sell product videos. Sample: https://cdn.scenema.ai/public/content/voice/juma/sample-pro-v2.mp3 - **Neema** (female, sw): A comforting, patient female voice in Swahili with a calm, steady pace. Ideal for lessons, health information and supportive guidance. Sample: https://cdn.scenema.ai/public/content/voice/neema/sample-pro-v2.mp3 - **Amani** (female, sw-KE): A crisp, eager female voice in Kenyan Swahili with a low, warm tone. Suited to stories, wellness content and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/amani/sample-pro-v2.mp3 - **Baraka** (male, sw-KE): A confident, clear male voice in Kenyan Swahili with a low, composed tone. Built for legal, financial and corporate explainers. Sample: https://cdn.scenema.ai/public/content/voice/baraka/sample-pro-v2.mp3 ### Tamil (4 voices) - **Karthik** (male, ta): A confident, clear young male voice in Tamil with an influencer feel. Made for social ads, app promos and launch videos aimed at young audiences. Sample: https://cdn.scenema.ai/public/content/voice/karthik/sample-pro-v2.mp3 - **Meena** (female, ta): A warm, engaging female voice in Tamil with a calm, teacherly pace. Ideal for lessons, patient education and clear explainers. Sample: https://cdn.scenema.ai/public/content/voice/meena/sample-pro-v2.mp3 - **Janani** (female, ta-IN): A professional yet approachable female voice in Tamil with a relaxed, conversational flow. Great for brand stories, creator videos and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/janani/sample-pro-v2.mp3 - **Senthil** (male, ta-IN): A natural, clear male voice in Tamil with a low, steady tone. Built for legal explainers, financial guidance and trusted corporate messaging. Sample: https://cdn.scenema.ai/public/content/voice/senthil/sample-pro-v2.mp3 ### Telugu (4 voices) - **Ravi** (male, te): A young male voice in Telugu with a curious, peer to peer tone. Suits fashion and lifestyle ads, app promos and casual social content. Sample: https://cdn.scenema.ai/public/content/voice/ravi/sample-pro-v2.mp3 - **Lakshmi** (female, te-IN): A confident, clear female voice in Telugu with a bright, upbeat podcast style. Great for wellness content, creator videos and lively explainers. Sample: https://cdn.scenema.ai/public/content/voice/lakshmi/sample-pro-v2.mp3 - **Sravani** (female, te-IN): A warm, engaging female voice in Telugu with a bright tone and a patient teaching pace. Ideal for lessons, explainers and patient education. Sample: https://cdn.scenema.ai/public/content/voice/sravani/sample-pro-v2.mp3 - **Srinivas** (male, te-IN): A warm, engaging male voice in Telugu with a low, assured tone. Built for legal and financial explainers, corporate training and public information. Sample: https://cdn.scenema.ai/public/content/voice/srinivas/sample-pro-v2.mp3 ### Thai (4 voices) - **Nattapong** (male, th): A warm, engaging male voice in his early twenties for Thai social ads, beauty and lifestyle promos. Friendly and fresh, he appeals to young shoppers. Sample: https://cdn.scenema.ai/public/content/voice/nattapong/sample-pro-v2.mp3 - **Ploy** (female, th): An enthusiastic, fun female voice in her mid thirties for Thai podcasts, YouTube commentary and promos. Bright and engaging, she keeps audiences entertained. Sample: https://cdn.scenema.ai/public/content/voice/ploy/sample-pro-v2.mp3 - **Pranee** (female, th): A cool, confident female voice in her late forties for Thai courses, corporate training and onboarding. Composed and collaborative, she keeps learners focused. Sample: https://cdn.scenema.ai/public/content/voice/pranee/sample-pro-v2.mp3 - **Somchai** (male, th): A laid back, encouraging male voice in his mid fifties for Thai finance, investment and insurance content. Relaxed and wise, he makes money talk comfortable. Sample: https://cdn.scenema.ai/public/content/voice/somchai/sample-pro-v2.mp3 ### Turkish (4 voices) - **Elif** (female, tr): A calm, reassuring female voice in her late thirties for Turkish explainers, fun facts channels and course lessons. She makes curious topics easy and relaxing to follow. Sample: https://cdn.scenema.ai/public/content/voice/elif/sample-pro-v2.mp3 - **Emre** (male, tr): A bold, confident male voice in his early twenties for Turkish social ads, launches and trailers. Clear and punchy, he gives short spots real momentum. Sample: https://cdn.scenema.ai/public/content/voice/emre/sample-pro-v2.mp3 - **Gulsen** (female, tr): A clear, friendly female voice in her sixties for Turkish stories, family content and heritage brand films. She tells a tale with the warmth of a favorite grandmother. Sample: https://cdn.scenema.ai/public/content/voice/gulsen/sample-pro-v2.mp3 - **Murat** (male, tr): A confident, clear male voice in his early thirties for Turkish patient education, pharma and public health videos. He explains medical facts with calm assurance. Sample: https://cdn.scenema.ai/public/content/voice/murat/sample-pro-v2.mp3 ### Urdu (4 voices) - **Ayesha** (female, ur): A deep, velvety female voice in her early thirties for Urdu lessons, documentaries and history content. Unhurried and graceful, she rewards close listening. Sample: https://cdn.scenema.ai/public/content/voice/ayesha/sample-pro-v2.mp3 - **Faisal** (male, ur): A clear, confident male voice in his early forties for Urdu medical, pharma and safety content. Precise and calm, he sounds like a trusted doctor. Sample: https://cdn.scenema.ai/public/content/voice/faisal/sample-pro-v2.mp3 - **Rukhsana** (female, ur): A relaxed, encouraging female voice in her late fifties for Urdu stories, wellness and nonprofit films. Laid back and kind, she feels like family. Sample: https://cdn.scenema.ai/public/content/voice/rukhsana/sample-pro-v2.mp3 - **Zain** (male, ur): A polished, approachable male voice in his mid twenties for Urdu social ads, app promos and ecommerce. Professional and fresh, he speaks to young buyers. Sample: https://cdn.scenema.ai/public/content/voice/zain/sample-pro-v2.mp3 ### Vietnamese (4 voices) - **Linh** (female, vi-VN): A medium pitched young Vietnamese female voice that sounds confident and clear. Good for lessons, app explainers and onboarding videos. Sample: https://cdn.scenema.ai/public/content/voice/linh/sample-pro-v2.mp3 - **Minh** (male, vi-VN): A low Vietnamese male voice that is light, airy and precise. A friendly fit for product ads, app promos and ecommerce spots. Sample: https://cdn.scenema.ai/public/content/voice/minh/sample-pro-v2.mp3 - **Quang** (male, vi-VN): A low Vietnamese male voice that sounds confident and clear with professional authority. Ideal for legal, finance and corporate explainers. Sample: https://cdn.scenema.ai/public/content/voice/quang/sample-pro-v2.mp3 - **Thuy** (female, vi-VN): A medium pitched Vietnamese female voice that is enthusiastic, engaging and fun. Great for stories, creator videos and lively explainers. Sample: https://cdn.scenema.ai/public/content/voice/thuy/sample-pro-v2.mp3 ### Afrikaans (2 voices) - **Annelie** (female, af): A thoughtful female voice with an intimate, talk show closeness. Suits Afrikaans video essays, reflective documentaries and calm lessons. Sample: https://cdn.scenema.ai/public/content/voice/annelie/sample-pro-v2.mp3 - **Pieter** (male, af): A mature, low male voice that sounds confident and clear, like a seasoned podcast host. Ideal for Afrikaans brand stories, company films and documentaries. Sample: https://cdn.scenema.ai/public/content/voice/pieter/sample-pro-v2.mp3 ### Albanian (2 voices) - **Arber** (male, sq): A young male voice with a low, even tone that feels professional yet approachable. Good for Albanian podcasts, wellness talks and employee onboarding. Sample: https://cdn.scenema.ai/public/content/voice/arber/sample-pro-v2.mp3 - **Arta** (female, sq): A bright, warm female voice with a teacher's encouraging tone. Fits Albanian lessons, online courses and step by step tutorials. Sample: https://cdn.scenema.ai/public/content/voice/arta/sample-pro-v2.mp3 ### Armenian (2 voices) - **Anahit** (female, hy): A deep, velvety female voice with an unhurried documentary pace. Made for Armenian nature films, heritage stories and premium brand narration. Sample: https://cdn.scenema.ai/public/content/voice/anahit/sample-pro-v2.mp3 - **Armen** (male, hy): A resonant, mature male voice with a quick wit and a quiz host's timing. Good for Armenian YouTube explainers, fun fact videos and podcasts. Sample: https://cdn.scenema.ai/public/content/voice/armen/sample-pro-v2.mp3 ### Assamese (2 voices) - **Bornali** (female, as): A young female voice that sounds natural and clear with an easy documentary flow. Suits Assamese nature films, science lessons and public information. Sample: https://cdn.scenema.ai/public/content/voice/bornali/sample-pro-v2.mp3 - **Pranjal** (male, as): A low, highly approachable male voice from the world of instructional video. Made for Assamese training modules, how to guides and software walkthroughs. Sample: https://cdn.scenema.ai/public/content/voice/pranjal/sample-pro-v2.mp3 ### Azerbaijani (2 voices) - **Elvin** (male, az): A deep, velvety male voice with the unhurried rhythm of a long form interviewer. Suits Azerbaijani podcasts, documentaries and premium brand films. Sample: https://cdn.scenema.ai/public/content/voice/elvin/sample-pro-v2.mp3 - **Leyla** (female, az): A resonant female voice with a teacher's clarity and a touch of wit. Good for Azerbaijani lessons, product tours and explainer videos that keep attention. Sample: https://cdn.scenema.ai/public/content/voice/leyla/sample-pro-v2.mp3 ### Basque (2 voices) - **Itziar** (female, eu): A textured, resonant female voice with a librarian's soothing calm. Made for Basque lessons, heritage stories and patient education. Sample: https://cdn.scenema.ai/public/content/voice/itziar/sample-pro-v2.mp3 - **Nacho** (male, eu): A resonant male voice with a radio host's warmth and quick wit. Good for Basque podcasts, event promos and conversational brand videos. Sample: https://cdn.scenema.ai/public/content/voice/nacho/sample-pro-v2.mp3 ### Belarusian (2 voices) - **Alesia** (female, be): A warm female voice with a conversational tone and a dry sense of humor. Suits Belarusian lessons, strategy explainers and software tutorials. Sample: https://cdn.scenema.ai/public/content/voice/alesia/sample-pro-v2.mp3 - **Uladzislau** (male, be): A young male voice that is laid back, encouraging and easy to listen to. Good for Belarusian YouTube channels, app explainers and casual tutorials. Sample: https://cdn.scenema.ai/public/content/voice/uladzislau/sample-pro-v2.mp3 ### Bulgarian (2 voices) - **Desislava** (female, bg): A bright young female voice that sounds confident and clear. Made for Bulgarian nature documentaries, science explainers and travel films. Sample: https://cdn.scenema.ai/public/content/voice/desislava/sample-pro-v2.mp3 - **Georgi** (male, bg): A young male voice with a low, confident and clear public radio delivery. Suits Bulgarian training videos, software tutorials and product onboarding. Sample: https://cdn.scenema.ai/public/content/voice/georgi/sample-pro-v2.mp3 ### Burmese (2 voices) - **Khin** (female, my): A low female voice with a comforting, steady tone, as if calming someone who is stressed. Ideal for Burmese health education, wellness and gentle documentaries. Sample: https://cdn.scenema.ai/public/content/voice/khin/sample-pro-v2.mp3 - **Thant** (male, my): A mature, low male voice that sounds confident and clear, with a librarian's patience. Good for Burmese history, lessons and civic information. Sample: https://cdn.scenema.ai/public/content/voice/thant/sample-pro-v2.mp3 ### Catalan (2 voices) - **Jordi** (male, ca): A relaxed, low male voice with a counselor's reassuring ease. Good for Catalan wellness content, HR programs and supportive help center videos. Sample: https://cdn.scenema.ai/public/content/voice/jordi/sample-pro-v2.mp3 - **Montse** (female, ca): A female voice with a curious, peer to peer tone that invites the listener in. Suits Catalan software explainers, lessons and onboarding videos. Sample: https://cdn.scenema.ai/public/content/voice/montse/sample-pro-v2.mp3 ### Cebuano (2 voices) - **Jocelyn** (female, ceb): A bright, energetic female voice with colorful, quick delivery. Great for Cebuano lessons, kids learning and upbeat app explainers. Sample: https://cdn.scenema.ai/public/content/voice/jocelyn/sample-pro-v2.mp3 - **Rodel** (male, ceb): A low male voice that sounds confident and clear, like a host running a brainstorm. Suits Cebuano business explainers, company updates and podcasts. Sample: https://cdn.scenema.ai/public/content/voice/rodel/sample-pro-v2.mp3 ### Croatian (2 voices) - **Marko** (male, hr): A relaxed, mature male voice that sounds confident and clear, like a veteran host on the couch. Good for Croatian history, trivia and travel stories. Sample: https://cdn.scenema.ai/public/content/voice/marko/sample-pro-v2.mp3 - **Petra** (female, hr): A cool, confident female voice with a professor's collaborative tone. Made for Croatian online courses, professional training and technical explainers. Sample: https://cdn.scenema.ai/public/content/voice/petra/sample-pro-v2.mp3 ### Czech (2 voices) - **Jakub** (male, cs): A laid back, encouraging male voice in Czech with a low, mature radio tone. Great for podcasts, commentary and relaxed explainers. Sample: https://cdn.scenema.ai/public/content/voice/jakub/sample-pro-v2.mp3 - **Tereza** (female, cs): A professional yet approachable young female voice in Czech with a bright tone. Ideal for lessons, tutorials and onboarding videos. Sample: https://cdn.scenema.ai/public/content/voice/tereza/sample-pro-v2.mp3 ### Danish (2 voices) - **Freja** (female, da): A female voice with an objective, direct and helpful tone. Suits Danish explainers, documentaries and product walkthroughs that need plain clarity. Sample: https://cdn.scenema.ai/public/content/voice/freja/sample-pro-v2.mp3 - **Mads** (male, da): A young male voice that is enthusiastic, engaging and fun, with a coach's encouragement. Great for Danish wellness, fitness and motivational content. Sample: https://cdn.scenema.ai/public/content/voice/mads/sample-pro-v2.mp3 ### Estonian (2 voices) - **Kadri** (female, et): A calm female voice with a reflective, reassuring professor's tone. Made for Estonian courses, patient education and thoughtful explainers. Sample: https://cdn.scenema.ai/public/content/voice/kadri/sample-pro-v2.mp3 - **Rasmus** (male, et): A low male voice that sounds confident and clear with a cinematic storyteller's touch. Good for Estonian brand films, documentaries and narrative stories. Sample: https://cdn.scenema.ai/public/content/voice/rasmus/sample-pro-v2.mp3 ### Finnish (2 voices) - **Aino** (female, fi): A bright female voice with a teacher's clarity and an intimate, talk show closeness. Suits Finnish lessons, onboarding and personal explainer videos. Sample: https://cdn.scenema.ai/public/content/voice/aino/sample-pro-v2.mp3 - **Mikko** (male, fi): A low male voice with a professor's knowledge and a professional yet approachable tone. Good for Finnish technical explainers, B2B overviews and training. Sample: https://cdn.scenema.ai/public/content/voice/mikko/sample-pro-v2.mp3 ### Galician (2 voices) - **Inigo** (male, gl): A low male voice with a radio host's professional yet approachable manner. Suits Galician podcasts, company updates and friendly product explainers. Sample: https://cdn.scenema.ai/public/content/voice/inigo/sample-pro-v2.mp3 - **Uxia** (female, gl): A low, mature female voice that sounds confident and clear with a public radio poise. Made for Galician documentaries, heritage stories and civic information. Sample: https://cdn.scenema.ai/public/content/voice/uxia/sample-pro-v2.mp3 ### Georgian (2 voices) - **Giorgi** (male, ka): A low, laid back male voice with an encouraging, easy storytelling feel. Suits Georgian travel stories, brand films and YouTube narration. Sample: https://cdn.scenema.ai/public/content/voice/giorgi/sample-pro-v2.mp3 - **Nino** (female, ka): A bright yet relaxed female voice with a patient instructor's pacing. Good for Georgian lessons, how to guides and software tutorials. Sample: https://cdn.scenema.ai/public/content/voice/nino/sample-pro-v2.mp3 ### Greek (2 voices) - **Eleni** (female, el-GR): A confident, clear female voice in Greek with a bright, thoughtful tone. Ideal for history, culture and calm educational narration. Sample: https://cdn.scenema.ai/public/content/voice/eleni/sample-pro-v2.mp3 - **Nikos** (male, el-GR): A resonant, witty male voice in Greek with a low, lively tone. Made for instructional videos, creator content and engaging explainers. Sample: https://cdn.scenema.ai/public/content/voice/nikos/sample-pro-v2.mp3 ### Gujarati (2 voices) - **Hetal** (female, gu): A deep, velvety mature female voice with unhurried documentary pacing. Made for Gujarati documentaries, heritage films and premium brand stories. Sample: https://cdn.scenema.ai/public/content/voice/hetal/sample-pro-v2.mp3 - **Jignesh** (male, gu): A low male voice with an interviewer's professional yet approachable manner. Good for Gujarati business explainers, finance videos and podcasts. Sample: https://cdn.scenema.ai/public/content/voice/jignesh/sample-pro-v2.mp3 ### Haitian Creole (2 voices) - **Wideline** (female, ht): A bright young female voice that is warm and engaging. Suits Haitian Creole public health messages, lessons and community stories. Sample: https://cdn.scenema.ai/public/content/voice/wideline/sample-pro-v2.mp3 - **Wilson** (male, ht): A young male voice with a broadcaster's professional yet approachable delivery. Good for Haitian Creole news explainers, civic information and product promos. Sample: https://cdn.scenema.ai/public/content/voice/wilson/sample-pro-v2.mp3 ### Hungarian (2 voices) - **László** (male, hu): A low, highly approachable male voice with an easy, familiar warmth. Good for Hungarian onboarding, customer support and family focused brand videos. Sample: https://cdn.scenema.ai/public/content/voice/laszlo/sample-pro-v2.mp3 - **Zsófia** (female, hu): A young female voice with an objective, direct and helpful tone. Suits Hungarian product explainers, help center videos and science content. Sample: https://cdn.scenema.ai/public/content/voice/zsofia/sample-pro-v2.mp3 ### Icelandic (2 voices) - **Gunnar** (male, is): A low male voice with a parent's patience and a professional yet approachable tone. Suits Icelandic onboarding, how to guides and public information. Sample: https://cdn.scenema.ai/public/content/voice/gunnar/sample-pro-v2.mp3 - **Sigrún** (female, is): A bright, highly approachable female voice with a documentary narrator's calm. Made for Icelandic nature films, tourism videos and sustainability stories. Sample: https://cdn.scenema.ai/public/content/voice/sigrun/sample-pro-v2.mp3 ### Javanese (2 voices) - **Hafiz** (male, jv): A low, confident male voice for Javanese podcasts, talk segments and clear conversational explainers. Steady and direct with a friendly edge. Sample: https://cdn.scenema.ai/public/content/voice/hafiz/sample-pro-v2.mp3 - **Wulan** (female, jv): A young female voice that is warm and engaging with a lecturer's clarity. Good for Javanese lessons, app explainers and community health videos. Sample: https://cdn.scenema.ai/public/content/voice/wulan/sample-pro-v2.mp3 ### Kannada (2 voices) - **Kavya** (female, kn): A caring, professional woman in her late forties speaking Kannada with a light Telugu accent. Bright and approachable, she suits support, public service and community health content. Sample: https://cdn.scenema.ai/public/content/voice/kavya/sample-pro-v2.mp3 - **Prakash** (male, kn): A lively, higher male voice for Kannada stories and talk style explainers. Objective and helpful, with a direct, upbeat delivery. Sample: https://cdn.scenema.ai/public/content/voice/prakash/sample-pro-v2.mp3 ### Kazakh (2 voices) - **Aigerim** (female, kk): A calm, reflective female voice for Kazakh nature documentaries and thoughtful explainers. Reassuring and clear with a gentle lift. Sample: https://cdn.scenema.ai/public/content/voice/aigerim/sample-pro-v2.mp3 - **Nurlan** (male, kk): A low, calm male voice for reflective Kazakh narration. Warm and reassuring, suited to counseling, wellbeing and thoughtful talks. Sample: https://cdn.scenema.ai/public/content/voice/nurlan/sample-pro-v2.mp3 ### Lao (2 voices) - **Bouakham** (female, lo): A warm, mature female voice for Lao nature stories and gentle explainers. Conversational with a touch of dry humor. Sample: https://cdn.scenema.ai/public/content/voice/bouakham/sample-pro-v2.mp3 - **Khamphet** (male, lo): A fast, articulate young male voice for Lao radio style podcasts, promos and news roundups. Energetic, low and punchy. Sample: https://cdn.scenema.ai/public/content/voice/khamphet/sample-pro-v2.mp3 ### Latvian (2 voices) - **Jānis** (male, lv): A medium, approachable male voice for Latvian legal, financial and business explainers. Clear, friendly and trustworthy. Sample: https://cdn.scenema.ai/public/content/voice/janis/sample-pro-v2.mp3 - **Laura** (female, lv): A young, low and highly approachable female voice for thoughtful Latvian explainers, essays and calm learning content. Sample: https://cdn.scenema.ai/public/content/voice/laura/sample-pro-v2.mp3 ### Lithuanian (2 voices) - **Gabija** (female, lt): A clear, friendly female voice for Lithuanian lessons and tutorials. Patient and precise, with a light, encouraging tone. Sample: https://cdn.scenema.ai/public/content/voice/gabija/sample-pro-v2.mp3 - **Mantas** (male, lt): A young, low male voice for Lithuanian podcasts and news explainers. Objective, direct and helpful. Sample: https://cdn.scenema.ai/public/content/voice/mantas/sample-pro-v2.mp3 ### Luxembourgish (2 voices) - **Monique** (female, lb): A low, warm female voice for Luxembourgish lectures and explainers. Calm, conversational and lightly witty. Sample: https://cdn.scenema.ai/public/content/voice/monique/sample-pro-v2.mp3 - **Romain** (male, lb): A low, warm male voice for Luxembourgish stories, heritage films and reflective narration. Engaging and unhurried. Sample: https://cdn.scenema.ai/public/content/voice/romain/sample-pro-v2.mp3 ### Macedonian (2 voices) - **Marija** (female, mk): An approachable woman in her early forties speaking Macedonian with a light Polish accent. Her low, calm delivery suits tutorials, courses and workplace training. Sample: https://cdn.scenema.ai/public/content/voice/marija/sample-pro-v2.mp3 - **Zoran** (male, mk): A medium, intimate male voice for Macedonian stories and talk style podcasts. Warm, personal and conversational. Sample: https://cdn.scenema.ai/public/content/voice/zoran/sample-pro-v2.mp3 ### Maithili (2 voices) - **Abhishek** (male, mai): A young, low male voice for Maithili podcasts and interviews. Warm, engaging and full of ideas. Sample: https://cdn.scenema.ai/public/content/voice/abhishek/sample-pro-v2.mp3 - **Archana** (female, mai): A cool, confident female voice for Maithili explainers and collaborative learning content. Clear and composed. Sample: https://cdn.scenema.ai/public/content/voice/archana/sample-pro-v2.mp3 ### Malay (2 voices) - **Aisyah** (female, ms): A fast, articulate female voice for Malay nature and science explainers. Bright, energetic and clear. Sample: https://cdn.scenema.ai/public/content/voice/aisyah/sample-pro-v2.mp3 - **Azman** (male, ms): A deep, velvety male voice for Malay stories, brand films and premium narration. Unhurried and rich. Sample: https://cdn.scenema.ai/public/content/voice/azman/sample-pro-v2.mp3 ### Malayalam (2 voices) - **Anagha** (female, ml): A warm, engaging young female voice for Malayalam documentaries and calm explainers. Clear, public radio style. Sample: https://cdn.scenema.ai/public/content/voice/anagha/sample-pro-v2.mp3 - **Suresh** (male, ml): A crisp, eager male voice for Malayalam quizzes, podcasts and fun explainers. Low, bright and lively. Sample: https://cdn.scenema.ai/public/content/voice/suresh/sample-pro-v2.mp3 ### Mongolian (2 voices) - **Oyunaa** (female, mn): A clear, articulate female voice for Mongolian training walkthroughs and instructions. Precise and steady. Sample: https://cdn.scenema.ai/public/content/voice/oyunaa/sample-pro-v2.mp3 - **Temuulen** (male, mn): A low, highly approachable male voice for Mongolian radio, podcasts and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/temuulen/sample-pro-v2.mp3 ### Nepali (2 voices) - **Bikash** (male, ne): A low, curious male voice for Nepali podcasts and conversations. Peer to peer and genuinely interested. Sample: https://cdn.scenema.ai/public/content/voice/bikash/sample-pro-v2.mp3 - **Sabina** (female, ne): A youthful, vibrant female voice for Nepali pop culture, gaming and social content. Bright and energetic. Sample: https://cdn.scenema.ai/public/content/voice/sabina/sample-pro-v2.mp3 ### Norwegian Bokmål (2 voices) - **Ingrid** (female, nb): A breezy, light female voice for Norwegian lifestyle, travel and relaxed brand content. Sample: https://cdn.scenema.ai/public/content/voice/ingrid/sample-pro-v2.mp3 - **Lars** (male, nb): A crisp, eager young male voice for Norwegian podcasts, tech explainers and startup content. Sample: https://cdn.scenema.ai/public/content/voice/lars/sample-pro-v2.mp3 ### Odia (2 voices) - **Debasis** (male, or): A low, curious male voice for Odia podcasts and community explainers. Peer to peer and friendly. Sample: https://cdn.scenema.ai/public/content/voice/debasis/sample-pro-v2.mp3 - **Sasmita** (female, or): A smooth, polished female voice for Odia e-learning and marketing. Mellow, clear and professional. Sample: https://cdn.scenema.ai/public/content/voice/sasmita/sample-pro-v2.mp3 ### Pashto (2 voices) - **Ahmad** (male, ps): A low, intimate male voice for Pashto talk shows, podcasts and personal stories. Warm and close. Sample: https://cdn.scenema.ai/public/content/voice/ahmad/sample-pro-v2.mp3 - **Malalai** (female, ps): A warm, engaging female voice for Pashto legal and advisory explainers. Authoritative yet personal. Sample: https://cdn.scenema.ai/public/content/voice/malalai/sample-pro-v2.mp3 ### Punjabi (2 voices) - **Gurdeep** (male, pa): A low, natural and clear male voice for Punjabi stories, documentaries and heritage content. Sample: https://cdn.scenema.ai/public/content/voice/gurdeep/sample-pro-v2.mp3 - **Harpreet** (female, pa): A young, bright female voice for Punjabi social ads, product promos and influencer style content. Sample: https://cdn.scenema.ai/public/content/voice/harpreet/sample-pro-v2.mp3 ### Romanian (2 voices) - **Cristian** (male, ro): A low, professional yet approachable male voice for Romanian documentaries, explainers and corporate films. Sample: https://cdn.scenema.ai/public/content/voice/cristian/sample-pro-v2.mp3 - **Ioana** (female, ro): A clear, friendly young female voice for Romanian podcasts, radio and lifestyle explainers. Sample: https://cdn.scenema.ai/public/content/voice/ioana/sample-pro-v2.mp3 ### Serbian (2 voices) - **Milica** (female, sr): A low, professional yet approachable female voice for Serbian trivia, podcasts and bookish explainers. Sample: https://cdn.scenema.ai/public/content/voice/milica/sample-pro-v2.mp3 - **Nikola** (male, sr): A warm, mature male voice with a lighter pitch and dry humor for Serbian stories and explainers. Sample: https://cdn.scenema.ai/public/content/voice/nikola/sample-pro-v2.mp3 ### Sindhi (2 voices) - **Kishore** (male, sd): A friendly young man speaking Sindhi with a light accent from Delhi Urdu. His low, approachable voice suits cooking shows, recipe videos and relaxed how to content. Sample: https://cdn.scenema.ai/public/content/voice/kishore/sample-pro-v2.mp3 - **Sanam** (female, sd): A laid back, encouraging female voice for Sindhi finance and advisory explainers. Clear and assured. Sample: https://cdn.scenema.ai/public/content/voice/sanam/sample-pro-v2.mp3 ### Sinhala (2 voices) - **Chamara** (male, si): A relaxed, low male voice for Sinhala podcasts, interviews and easygoing explainers. Sample: https://cdn.scenema.ai/public/content/voice/chamara/sample-pro-v2.mp3 - **Nethmi** (female, si): A young, confident female voice for Sinhala tutorials and instructional videos. Bright and clear. Sample: https://cdn.scenema.ai/public/content/voice/nethmi/sample-pro-v2.mp3 ### Slovak (2 voices) - **Miroslav** (male, sk): A low, textured and resonant male voice for Slovak podcasts, documentaries and soothing narration. Sample: https://cdn.scenema.ai/public/content/voice/miroslav/sample-pro-v2.mp3 - **Zuzana** (female, sk): A bright, breezy female voice for Slovak training and instructional videos. Clear and upbeat. Sample: https://cdn.scenema.ai/public/content/voice/zuzana/sample-pro-v2.mp3 ### Slovenian (2 voices) - **Matjaž** (male, sl): A medium, objective and direct male voice for Slovenian radio, news and helpful explainers. Sample: https://cdn.scenema.ai/public/content/voice/matjaz/sample-pro-v2.mp3 - **Nina** (female, sl): A low, light and precise female voice for Slovenian legal, compliance and policy explainers. Sample: https://cdn.scenema.ai/public/content/voice/nina/sample-pro-v2.mp3 ### Swedish (2 voices) - **Erik** (male, sv): A clear, friendly low male voice for Swedish podcasts, interviews and app explainers. Sample: https://cdn.scenema.ai/public/content/voice/erik-sv/sample-pro-v2.mp3 - **Saga** (female, sv): A composed woman in her early thirties speaking Swedish with a light German accent. Deep, velvety and unhurried, she suits legal explainers, policy training and premium professional services. Sample: https://cdn.scenema.ai/public/content/voice/saga/sample-pro-v2.mp3 ### Ukrainian (2 voices) - **Kateryna** (female, uk): A relaxed, assured female voice for Ukrainian legal, finance and public service explainers. Sample: https://cdn.scenema.ai/public/content/voice/kateryna/sample-pro-v2.mp3 - **Taras** (male, uk): A deep, velvety and unhurried male voice for Ukrainian radio, documentaries and premium narration. Sample: https://cdn.scenema.ai/public/content/voice/taras/sample-pro-v2.mp3 ### Uzbek (2 voices) - **Dilnoza** (female, uz): A low, calm and reassuring female voice for Uzbek coaching, wellness and training content. Sample: https://cdn.scenema.ai/public/content/voice/dilnoza/sample-pro-v2.mp3 - **Rustam** (male, uz): A warm, low male voice in his late thirties that narrates Uzbek with an easy, engaging storyteller's flow. Well suited to creator videos, brand stories and friendly explainers. Sample: https://cdn.scenema.ai/public/content/voice/rustam/sample-pro-v2.mp3 ## 24. Key pages - [Homepage](https://scenema.ai): product overview, the explainer intake, and videos made in Scenema - [Styles](https://scenema.ai/styles): every animation style, by family - [Voices](https://scenema.ai/voices): every narration voice, with samples, filterable by language and accent - [Pricing](https://scenema.ai/pricing): the free plan and paid plans - [AI models](https://scenema.ai/ai-models): the image and video models Scenema runs - [Scenema Audio](https://scenema.ai/audio): the speech engine for narration, voiceover and voice cloning - [Docs](https://scenema.ai/docs): how Scenema works and how to make a first video - [MCP server docs](https://scenema.ai/docs/api/mcp): using Scenema from Claude, ChatGPT, Cursor and other assistants - [Articles](https://scenema.ai/articles): guides on long-form AI animation, YouTube explainers and character consistency - [llms.txt](https://scenema.ai/llms.txt): a short summary of Scenema for language models