GET

/v1/schemas/together/audio/audio%2Ftranscriptions

kind inputactivity audiohash e320390c…extracted Aug 15, 2026version currentsource upstream spec ↗

Request body

10 properties · 1 required · 2 $defs
propertytypedescriptionconstraints
file*string | stringAudio 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 …
modelenumModel to use for transcriptionopenai/whisper-large-v3 · default: "openai/whisper-large-v3"
languagestringOptional ISO 639-1 language code. If `auto` is provided, language is auto-detected.default: "en"
promptstringOptional 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_formatenumThe format of the responsejson | verbose_json · default: "json"
temperaturenumberSampling temperature between 0.0 and 1.00 ≤ n ≤ 1 · default: 0
timestamp_granularitiesenum | 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"
diarizebooleanWhether to enable speaker diarization. When enabled, you will get the speaker id for each word in the transcription. In the response, in the words array, you will get the speaker id for each word. In addition, we also return the speaker_segments array which co…default: false
min_speakersintegerMinimum number of speakers expected in the audio. Used to improve diarization accuracy when the approximate number of speakers is known.
max_speakersintegerMaximum number of speakers expected in the audio. Used to improve diarization accuracy when the approximate number of speakers is known.

Validate a payload

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