GET

/v1/schemas/fal/audio/fal-ai/stable-audio-25/text-to-audio

Accept:

kind inputactivity audiohash 4a63d555…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `d294144a215065bdd455a3959d6eba12a2579ef9db7ea1baa7dfbd234c0f8439` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	The prompt to generate audio from
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
seconds_total	integer	The duration of the audio clip to generate	1 ≤ n ≤ 190 · default: 190
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
num_inference_steps	integer	The number of steps to denoise the audio for	4 ≤ n ≤ 8 · default: 8
guidance_scale	number	How strictly the diffusion process adheres to the prompt text (higher values make your audio closer to your prompt).	1 ≤ n ≤ 25 · default: 1
seed	integer		nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/stable-audio-25/text-to-audio","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}