GET

/v1/schemas/fal/audio/fal-ai%2Fsam-audio%2Fspan-separate

kind inputactivity audiohash d0607ebfextracted Jul 6, 2026version currentsource upstream spec ↗

Request body

10 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
audio_url*stringURL of the audio file to process.
spans*AudioTimeSpan[]Time spans where the target sound occurs which should be isolated.
output_formatenumOutput audio format.wav | mp3 · default: "wav"
chunk_overlapnumberOverlap duration (in seconds) between chunks for crossfade blending.0 ≤ n ≤ 30 · default: 5
promptstringText prompt describing the sound to isolate. Optional but recommended - helps the model identify what type of sound to extract from the span.nullable
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. Requires text prompt; ignored for span-only separation.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
trim_to_spanbooleanTrim output audio to only include the specified span time range. If False, returns the full audio length with the target sound isolated throughout.default: false
use_sound_activity_rankingbooleanUse sound activity detection to rank reranking candidates based on how well each candidate's non-silent regions match the provided spans. Enables effective reranking even without a text prompt (span-only separation). Requires reranking_candidates > 1.default: false

Validate a payload

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