API docs/workflows/avatar-to-video

Avatar to video

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

Requiressource.textavatar.url
media: moving-imagevoice-over: on by defaultmusic: off by defaultcaptions: on by defaultratio: 9:16 by default

Build your request

Only the parameters that apply to avatar-to-video are shown. Set values on the left, copy the payload on the right.

View as Markdown (for LLMs)
source.textrequired

The exact script to be spoken. For script-to-video it can also be an X/Twitter or LinkedIn post URL: the post content becomes the script.

avatar.enabled

Show a talking avatar in the video.

avatar.urlrequired

Image (png/jpg/webp) or video of the avatar.

{
  "workflow": "avatar-to-video",
  "source": {
    "text": "Welcome to our product tour!"
  },
  "avatar": {
    "enabled": true,
    "url": "https://cdn.revid.ai/ai-gen/chSmd-WtE.jpg"
  }
}
Free, no API key needed.

Good to know

  • avatar.url accepts an image (png/jpg/webp) or a video; mimeType is inferred from the extension when omitted.
  • media.bRollType (split-screen, fullscreen) mixes generated B-roll with the avatar.
  • media.placeAvatarInContext = true places the avatar inside the generated scenes.