GET

/v1/schemas/fal/audio/fal-ai/whisper?kind=output

kind outputactivity audiohash f811d287…extracted Nov 10, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
ffedaf4443aa345d8d16f3f7369fbfa60fbfe182bf2f3a2879645990865e664b
{
  "fetchedAt": 1794286801,
  "extractorVersion": "2",
  "verifiedAt": null
}

Response body

4 properties · 3 required · 2 $defs
propertytypedescriptionconstraints
diarization_segments*DiarizationSegment[]Speaker diarization segments of the audio file. Only present if diarization is enabled.
text*stringTranscription of the audio file
inferred_languages*enum[]List of languages that the audio file is inferred to be. Defaults to null.
chunksWhisperChunk[]Timestamp chunks of the audio filenullable

Types

2 $defs

DiarizationSegmentobject

speaker*stringSpeaker ID of the segment
timestamp*any[]Start and end timestamp of the segmentitems ≥ 2 · items ≤ 2

WhisperChunkobject

speakerstringSpeaker ID of the chunk. Only present if diarization is enabled.nullable
text*stringTranscription of the chunk
timestamp*any[]Start and end timestamp of the chunkitems ≥ 2 · items ≤ 2

Validate a payload

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