GET

/v1/schemas/fal/video/fal-ai/hunyuan-video-foley

Accept:

kind inputactivity videohash 28c297a7…extracted Oct 14, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9e113864098b0111b07841a4021331550f1cf083b6795dbcb4a41059bc58bb1f` { "fetchedAt": 1791954060, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 2 required · 0 $defs

property	type	description	constraints
text_prompt*	string	Text description of the desired audio (optional).
video_url*	string	The URL of the video to generate audio for.
seed	integer	Random seed for reproducible generation.	nullable
negative_prompt	string	Negative prompt to avoid certain audio characteristics.	default: "noisy, harsh"
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
num_inference_steps	integer	Number of inference steps for generation.	10 ≤ n ≤ 100 · default: 50
guidance_scale	number	Guidance scale for audio generation.	1 ≤ n ≤ 10 · default: 4.5

Validate a payload

before you spend tokens

shell

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