GET

/v1/schemas/fal/audio/fal-ai%2Fstable-audio-3%2Fsmall%2Fmusic%2Faudio-inpainting

kind inputactivity audiohash c15e1f37extracted Jul 6, 2026version currentsource upstream spec ↗

Request body

13 properties · 4 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringText description guiding how the masked region is regenerated.
mask_end_seconds*numberEnd of the region to regenerate, in seconds.0 ≤ n ≤ 120
audio_url*stringSource audio. Only the masked region is regenerated.
mask_start_seconds*numberStart of the region to regenerate, in seconds.0 ≤ n ≤ 120
bitratestringAudio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac).default: "192k"
seedintegerRandom seed for reproducible outputs. Omit for a random seed.nullable
guidance_scalenumberClassifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.0 ≤ n ≤ 25 · default: 1
enable_prompt_expansionbooleanIf True, the prompt will be expanded using an LLM for more detailed and higher quality results.default: false
output_formatenumContainer format for the generated audio output.mp3 | wav | flac | ogg | opus | m4a · +1 more · default: "mp3"
num_inference_stepsintegerNumber of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.1 ≤ n ≤ 100 · default: 8
negative_promptstringText description of qualities to avoid in the output.default: ""
sync_modebooleanIf True, the audio is returned inline as a data URI and the result is not saved to the request history.default: false
enable_safety_checkerbooleanEnable NSFW content safety checking.default: true

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/stable-audio-3/small/music/audio-inpainting","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}