GET
/v1/schemas/together/audio/audio/translations
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace468edbdc879c48f500ca284270663ccc30cd83aee57a4e6a4e7a5bc04603b543{
"fetchedAt": 1786771359,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
7 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| file* | string | string | Audio file upload or public HTTP/HTTPS URL. Supported formats: .wav, .mp3, .m4a, .webm, .flac, .ogg, .opus, .aac. Maximum duration 4 hours; longer audio is rejected with `audio_too_long`. Binary uploads are additionally capped at 80 MB (HTTP 413); URL-fetched … | |
| model | enum | Model to use for translation | openai/whisper-large-v3 · default: "openai/whisper-large-v3" |
| language | string | Target output language. Optional ISO 639-1 language code. If omitted, language is set to English. | default: "en" |
| prompt | string | Optional text to bias decoding. Supported only on Whisper-family models (e.g. `openai/whisper-large-v3`). Other STT models (e.g. `nvidia/parakeet-tdt-0.6b-v3`) accept the field for API compatibility but ignore it. | |
| response_format | enum | The format of the response | json | verbose_json · default: "json" |
| temperature | number | Sampling temperature between 0.0 and 1.0 | 0 ≤ n ≤ 1 · default: 0 |
| timestamp_granularities | enum | enum[] | Controls level of timestamp detail in verbose_json. Only used when response_format is verbose_json. Can be a single granularity or an array to get multiple levels. | default: "segment" |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"together","endpointId":"audio/translations","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}