GET

/v1/schemas/fal/video/fal-ai/sync-lipsync/v3/image-to-video

kind inputactivity videohash da7d4071…extracted Oct 22, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
c960e3c62c50cf26c93c5219331af06a40b35a04c9955988594d5823f14e6e1f
{
  "fetchedAt": 1792645225,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

3 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
audio_url*stringURL of the input audio. The output video matches its duration.
image_url*stringURL of the input image. sync-3 animates the face in the image so it lip-syncs to the provided audio (image-to-video). Supported image formats: JPEG, PNG and WebP.
enable_safety_checkerbooleandefault: true

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/sync-lipsync/v3/image-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}