GET
/v1/schemas/llmgateway/audio/v1%2Faudio%2Ftranscriptions
Accept:
Request body
9 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| model* | string | ID of the transcription (speech-to-text) model to use. | |
| file | string | The audio file to transcribe. Required unless `url` is provided. | format: binary |
| url | string | URL of an audio file to download and transcribe upstream. Required unless `file` is provided. | |
| language | string | Language code (e.g. 'en'). When set, enables inverse text normalization so numbers and currencies are formatted in their written form. | |
| diarize | string | When 'true', enables speaker diarization; each word in the response includes a `speaker` field. | |
| filler_words | string | When 'true', filler words (e.g. 'uh', 'um') are kept in the transcript instead of being removed. | |
| keyterm | string | A key term to bias transcription toward (e.g. product names). Repeat the field for multiple terms. | |
| safety_identifier | string | Opaque end-user identifier stored in log params.safety_identifier. Never forwarded upstream and never replaces LLM Gateway's provider-facing identifier. | length ≤ 128 |
| user | string | Legacy end-user identifier, recorded as params.safety_identifier when safety_identifier is absent and it is at most 128 characters. Never forwarded upstream. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"llmgateway","endpointId":"v1/audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}