GET
/v1/schemas/fal/audio/fal-ai/elevenlabs/speech-to-text?kind=output
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above.Source tracedc13eba13a9cec97d8cc63aa140fb541e005ac9195996572cca694297fc5206f{
"fetchedAt": 1783329487,
"extractorVersion": "1",
"verifiedAt": null
} |
Response body
4 properties · 4 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| words* | TranscriptionWord[] | Word-level transcription details | |
| language_code* | string | Detected or specified language code | |
| language_probability* | number | Confidence in language detection | |
| text* | string | The full transcribed text |
Types
1 $defsTranscriptionWordobject
| type* | string | Type of element (word, spacing, or audio_event) | |
| speaker_id | string | Speaker identifier if diarization was enabled | nullable |
| end | number | End time in seconds | nullable |
| text* | string | The transcribed word or audio event | |
| start | number | Start time in seconds | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/elevenlabs/speech-to-text","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}