Public API v3

Create videos programmatically

One endpoint, ten workflows. Pick what you start from - a script, a prompt, a link, or a file - and the API handles visuals, voice-over, captions, and music. Every render call costs 10 credits plus generation costs, and you can estimate any payload for free before running it.

Full API reference Get your API key

What are you starting from?

The workflow field decides everything else - required input, defaults, and which parameters apply.

A script - the exact words to be spoken

Script to video

Turn a written script into a voiced, captioned video with AI visuals.

Avatar to video

A talking avatar (from a photo or video) reads your script, with optional B-roll.

Static background video

Voiced captions over a looping background (gameplay, satisfying clips, ...).

An idea or topic - the AI writes the script

Prompt to video

Describe the video you want; the AI writes the script and generates everything.

Ad generator

Generate a product ad from a prompt and/or product images.

A link - article, music, or any web page

Article to video

Summarize any web page or article into a narrated short video.

Music to video

Generate a music video synced to a track (upload, YouTube, or Spotify link).

A file - audio or video to transform

Audio to video

Turn a podcast, voice note, or any audio/video URL into an illustrated video.

Caption video

Add animated captions (and optional B-roll) to an existing video.

Motion transfer

Transfer the motion of a source video onto a character image (face swap style).

Your first video in 3 steps

1 - Get a key

Grab your API key from your account settings. Send it in the key header on every call.

2 - Start a render

curl -X POST 'https://www.revid.ai/api/public/v3/render' \
  -H 'Content-Type: application/json' \
  -H 'key: YOUR_API_KEY' \
  -d '{
    "workflow": "script-to-video",
    "source": { "text": "Did you know honey never spoils?" },
    "webhookUrl": "https://your-server.com/revid/webhook"
  }'

3 - Get the result

The render is asynchronous: your webhookUrl is called when the video is ready, or poll the status endpoint with the pid you received.

curl 'https://www.revid.ai/api/public/v3/status?pid=YOUR_PID' \
  -H 'key: YOUR_API_KEY'

Pro tip

Configure a video visually on revid.ai/create, click Get API code, and reuse that exact payload here.

All workflows at a glance

What each workflow needs (●) and what you can customize (✓). Click a workflow to explore its parameters interactively.

Workflow	Requires	source	media	voice	captions	music	avatar	options	render
Script to video	source.text	●	✓	✓	✓	✓	✓	✓	✓
Prompt to video	source.prompt	●	✓	✓	✓	✓	—	✓	✓
Audio to video	source.url	●	✓	—	✓	✓	—	✓	✓
Music to video	source.url	●	✓	—	✓	✓	—	✓	✓
Article to video	source.url	●	✓	✓	✓	✓	—	✓	✓
Avatar to video	source.text + avatar.url	●	✓	✓	✓	✓	●	✓	✓
Static background video	source.text or source.url	●	✓	✓	✓	✓	—	✓	✓
Motion transfer	source.url + media.provided[] with 1 image (the target character)	●	●	✓	✓	✓	—	✓	✓
Caption video	source.url	●	✓	—	✓	✓	—	✓	✓
Ad generator	source.prompt or media.provided[]	●	✓	✓	✓	✓	—	✓	✓

● required✓ available— not used

More resources

Full API reference

Every endpoint and schema, with an in-page request runner.

MCP server & CLI

Let AI agents create videos via MCP, or use revid-cli from any terminal.

OpenAPI spec

Machine-readable schema with per-workflow request types.

Postman collection

One request per workflow plus curated recipes, ready to import.

Docs for LLMs

Markdown versions of these docs, optimized for AI agents. Also in llms.txt.