GET

/v1/schemas/llmgateway/audio/v1%2Faudio%2Ftranscriptions

kind inputactivity audiohash fa62273d…extracted Nov 20, 2026version currentsource upstream spec ↗

Request body

9 properties · 1 required · 0 $defs
propertytypedescriptionconstraints
model*stringID of the transcription (speech-to-text) model to use.
filestringThe audio file to transcribe. Required unless `url` is provided.format: binary
urlstringURL of an audio file to download and transcribe upstream. Required unless `file` is provided.
languagestringLanguage code (e.g. 'en'). When set, enables inverse text normalization so numbers and currencies are formatted in their written form.
diarizestringWhen 'true', enables speaker diarization; each word in the response includes a `speaker` field.
filler_wordsstringWhen 'true', filler words (e.g. 'uh', 'um') are kept in the transcript instead of being removed.
keytermstringA key term to bias transcription toward (e.g. product names). Repeat the field for multiple terms.
safety_identifierstringOpaque end-user identifier stored in log params.safety_identifier. Never forwarded upstream and never replaces LLM Gateway's provider-facing identifier.length ≤ 128
userstringLegacy 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 tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"llmgateway","endpointId":"v1/audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}