GET

/v1/schemas/fal/video/fal-ai/thinksound

Accept:

kind inputactivity videohash 499a0476…extracted Oct 24, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `ed4ad307214a4cd20f4b649e44dea5c5bd2ce9fc1f484edb04d326e378249f93` { "fetchedAt": 1792818001, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
video_url*	string	The URL of the video to generate the audio for.
prompt	string	A prompt to guide the audio generation. If not provided, it will be extracted from the video.	default: ""
cfg_scale	number	The classifier-free guidance scale for audio generation.	1 ≤ n ≤ 20 · default: 5
seed	integer	The seed for the random number generator	nullable
enable_safety_checker	boolean		default: true
num_inference_steps	integer	The number of inference steps for audio generation.	2 ≤ n ≤ 100 · default: 24
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	default: false

Validate a payload

before you spend tokens

shell

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