GET

/v1/schemas/fal/video/fal-ai/ai-avatar/multi

Accept:

kind inputactivity videohash b9b70536…extracted Nov 13, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `328a0263c3a6ec18bb874b2e081f44583934c9265c5aa909c4ba069f02046fc7` { "fetchedAt": 1794546001, "extractorVersion": "2", "verifiedAt": null }

Request body

10 properties · 3 required · 0 $defs

property	type	description	constraints
prompt*	string	The text prompt to guide video generation.
first_audio_url*	string	The URL of the Person 1 audio file (max 600 seconds).
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.
use_only_first_audio	boolean	Whether to use only the first audio file.	default: false
num_frames	integer	Number of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.	41 ≤ n ≤ 241 · default: 181
acceleration	enum	The acceleration level to use for generation.	none \| regular \| high · default: "regular"
second_audio_url	string	The URL of the Person 2 audio file (max 600 seconds).	nullable
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
resolution	enum	Resolution of the video to generate. Must be either 480p or 720p.	480p \| 720p · default: "480p"
seed	integer	Random seed for reproducibility. If None, a random seed is chosen.	0 ≤ n ≤ 4294967295 · default: 81

Validate a payload

before you spend tokens

shell

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