GET

/v1/schemas/fal/audio/fal-ai/stable-audio-25/inpaint

Accept:

kind inputactivity audiohash 0b86ff4d…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `17059a9a9fb8df582ed65c3a42c6aa4d98e71bfbffb11871b1fdebebe0da41de` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

10 properties · 2 required · 0 $defs

property	type	description	constraints
prompt*	string	The prompt to guide the audio generation
audio_url*	string	The audio clip to inpaint
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
mask_start	integer	The start point of the audio mask	0 ≤ n ≤ 190 · default: 30
seconds_total	integer	The duration of the audio clip to generate. If not provided, it will be set to the duration of the input audio.	1 ≤ n ≤ 190 · nullable
seed	integer		nullable
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
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
mask_end	integer	The end point of the audio mask	0 ≤ n ≤ 190 · default: 190
num_inference_steps	integer	The number of steps to denoise the audio for	4 ≤ n ≤ 8 · default: 8

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/inpaint","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}