GET

/v1/schemas/fal/video/fal-ai/latentsync

Accept:

kind inputactivity videohash 218cc8bd…extracted Oct 17, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `45753ad5f23a46c54a0259c835c66216caee291eeb235e1a358bc4f57b65dc77` { "fetchedAt": 1792213207, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 2 required · 0 $defs

property	type	description	constraints
video_url*	string	The URL of the video to generate the lip sync for.
audio_url*	string	The URL of the audio to generate the lip sync for.
seed	integer	Random seed for generation. If None, a random seed will be used.	nullable
loop_mode	enum	Video loop mode when audio is longer than video. Options: pingpong, loop	pingpong \| loop · nullable
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
guidance_scale	number	Guidance scale for the model inference	1 ≤ n ≤ 2 · default: 1

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/latentsync","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}