GET

/v1/schemas/fal/audio/fal-ai%2Fsam-audio%2Fseparate

kind inputactivity audiohash e10e4b0eextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

8 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
prompt*stringText prompt describing the sound to isolate.
audio_url*stringURL of the audio file to process (WAV, MP3, FLAC supported)
output_formatenumOutput audio format.wav | mp3 · default: "wav"
chunk_overlapnumberOverlap duration (in seconds) between chunks for crossfade blending.0 ≤ n ≤ 30 · default: 5
predict_spansbooleanAutomatically predict temporal spans where the target sound occurs.default: false
accelerationenumThe acceleration level to use.fast | balanced | quality · default: "balanced"
reranking_candidatesintegerNumber of candidates to generate and rank. Higher improves quality but increases latency and cost.1 ≤ n ≤ 7 · default: 1
max_chunk_durationnumberMaximum audio duration (in seconds) to process in a single pass. Longer audio will be chunked with overlap and blended.10 ≤ n ≤ 60 · default: 60

Validate a payload

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