Scenema API

There are two ways to use Scenema from code and from AI assistants.

• The REST API at https://api.scenema.ai/v1, on the Creator and Pro plans, makes narrations and videos with no one in the loop. A script becomes an MP3 in any Scenema voice, with word timings and SRT captions when you ask for them. That narration, or your own voiceover or soundtrack, becomes a finished video in any Scenema style. Every endpoint with its schemas is in the API reference.
• The Scenema MCP lets Claude, ChatGPT, Cursor, Windsurf, Claude Code and any MCP client drive the whole studio, on every plan, with the same Director, projects, credits and plan limits as the app. The MCP Integration page has the setup for each app and what it costs.

How a video is made through the API

1. Audio. Make a narration from a script with the Narration API, or upload your own voiceover or soundtrack with the Assets API.
2. Price. Optionally ask POST /v1/estimates what the video will cost and whether the workspace can cover it.
3. Video. Start it with the Video API: the audio, a style from scenema.ai/styles and a prompt. Get the MP4 by polling or a webhook.
4. Afterwards. Make the finished video in the other aspect ratio, or give it a new audio track in another language (Change a video).

Audio is the only input

A video through the API starts from one audio track. It takes no documents, slides, images or video. In the app, the Director reads any file you give it and works out the script and the look with you in a conversation. The API skips that conversation, so it starts from the audio, which fixes what is said and how long the video runs. To start from a script, make the narration first.

What you can do today

• Make, edit and export videos from any MCP client. See MCP Integration.
• Turn scripts into narration over HTTP, on Creator and Pro. See Narration API.
• Upload your own voiceover or soundtrack, as a file or by link. See Assets API.
• Turn narrations and your own audio into finished videos over HTTP, on Creator and Pro. See Video API.
• Get told when a narration or video is ready: pass webhookUrl on the request, or set a default once, and Scenema sends a signed webhook. Or hold a read open until it changes. See Webhooks and Polling.
• List every project in the workspace, and follow one project’s chapters and shots while they are made. See Projects.
• Read the account, its plan and its credits, and let a user delete their account. See Account.
• See every request with its payloads, credits and webhooks, and your usage this month, on the API page in Scenema or through the API. See Usage and requests.
• Create API keys for the Narration and Video APIs and for MCP clients that cannot sign in with your Scenema account, and disable or revoke them. See Managing API Keys.
• Send the key as a Bearer token. See Authentication.
• Rely on a per-plan request limit that returns a clear 429 when you reach it. See Rate Limits.