GET

/v1/schemas/fal/video/fal-ai/infinitalk

Accept:

kind inputactivity videohash 4fe051dd…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `a858bbe3937fb7d88aa1f2f9fc799c7475ce1a078758e7360612d182731ffc61` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

8 properties · 3 required · 0 $defs

property	type	description	constraints
audio_url*	string	The URL of the audio file.
prompt*	string	The text prompt to guide video generation.
image_url*	string	URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.
acceleration	enum	The acceleration level to use for generation.	none \| regular \| high · default: "regular"
seed	integer	Random seed for reproducibility. If None, a random seed is chosen.	0 ≤ n ≤ 4294967295 · default: 42
resolution	enum	Resolution of the video to generate. Must be either 480p or 720p.	480p \| 720p · default: "480p"
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
num_frames	integer	Number of frames to generate. Must be between 41 to 721.	41 ≤ n ≤ 721 · default: 145

Validate a payload

before you spend tokens

shell

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