GET

/v1/schemas/elevenlabs/audio/v1/audio-isolation/stream

kind inputactivity audiohash 3e985b1b…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
56793d52b38081086c43910ec1916ff4bb286322250511820c239e4f46831396
{
  "fetchedAt": 1783328734,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

2 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
audio*stringThe audio file from which vocals/speech will be isolated from.format: binary
file_formatenumThe format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform.pcm_s16le_16 | other · nullable

Validate a payload

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