GET

/v1/schemas/meta/audio/v1/asr/transcribe?kind=output

kind outputactivity audiohash caa8e9bd…extracted Oct 9, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

docs-derived

Source trace
09222e0ecdcf7fe022d2dafe5b31efc38840e6d0228d9e9146daf6bd68bdef03
{
  "fetchedAt": 1791523841,
  "extractorVersion": "1",
  "verifiedAt": null
}

Response body

4 properties · 4 required · 1 $defs
propertytypedescriptionconstraints
sessionId*stringThe sessionId query parameter, or the id the server generated when it was absent.
transcript*stringFinal transcript for the whole clip. Populated in every mode; in the multi-turn modes it is the turn transcripts joined in turn order.
audioDurationMs*integerTotal audio duration processed, in milliseconds.format: int64
turns*turn[]Every turn the model reported, in ascending turnId order. Empty in PUSH_TO_TALK. A turn the clip ended part-way through carries the boundaries the model gave and an empty transcript.

Types

1 $defs

turnobject

turnId*integerId for this turn. Turns are reported in ascending id order; numbering is not otherwise meaningful.format: int32
startMs*integerAudio processed when the model detected the turn's speech onset, in milliseconds from the start of the clip. Not a precise acoustic boundary.format: int64
endMs*integerAudio processed when the model detected the turn's speech end, in milliseconds from the start of the clip. Not a precise acoustic boundary.format: int64
transcript*stringFinalized transcript for this turn, including any post processing.
speakerstringModel-generated speaker label, such as A. Present in DIARIZATION only.

Validate a payload

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