Create audio transcription request

Transcribes audio into text

POST /audio/transcriptions

Python

Together AI SDK (v2)

# Docs for v1 can be found by changing the above selector ^
from together import Together

client = Together(
    api_key=os.environ.get("TOGETHER_API_KEY"),
)

file = open("audio.wav", "rb")

response = client.audio.transcriptions.create(
    model="openai/whisper-large-v3",
    file=file,
)

print(response.text)

200

{
  "text": "Hello, world!"
}

Authorizations

Authorization · string · header · default: default · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data

file · file string<uri> · required

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 500 MB (HTTP 413); URL-fetched audio is capped at 1 GB.

model · enum<string> · default: openai/whisper-large-v3

Model to use for transcription

Available options: openai/whisper-large-v3

language · string · default: en

Optional ISO 639-1 language code. If auto is provided, language is auto-detected.

Example:

"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<string> · default: json

The format of the response

Available options: json, verbose_json

temperature · number<float> · default: 0

Sampling temperature between 0.0 and 1.0

Required range: 0 <= x <= 1

timestamp_granularities · enum<string> enum<string>[] · default: segment

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.

Available options: segment, word

Example:

["word", "segment"]

diarize · boolean · default: false

Whether 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 contains the speaker id for each speaker segment along with the start and end time of the segment along with all the words in the segment.

For eg - ... "speaker_segments": [ "speaker_id": "SPEAKER_00", "start": 0, "end": 30.02, "words": [ { "id": 0, "word": "Tijana", "start": 0, "end": 11.475, "speaker_id": "SPEAKER_00" }, ...

min_speakers · integer

Minimum number of speakers expected in the audio. Used to improve diarization accuracy when the approximate number of speakers is known.

max_speakers · integer

Maximum number of speakers expected in the audio. Used to improve diarization accuracy when the approximate number of speakers is known.

Response

200

application/json

OK

Option 1

Option 2

text · string · required

The transcribed text

Example:

"Hello, world!"