Audio Transcriptions

POST
/v1/audio/transcriptions
chunking_strategy?null|
Defaultnull
diarize?boolean|null

If set to true, a speaker diarization will be done for this transcription.

Defaultfalse
filefile

The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

Formatbinary
language?string|null

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

model?string|null

ID of the model to use.

prompt?string|null

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

response_format?null|AudioOutputFormat
stream?boolean|null

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. Note: Streaming is not supported for the whisper models and will be ignored.

Defaultfalse
temperature?number|null

The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Default0
Formatfloat
Range0 <= value <= 1
timestamp_granularities?|null

The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment.

Default["segment"]

Response Body

application/json

curl -X POST "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/audio/transcriptions" \  -F file="string"
{
  "chunking_strategy": null,
  "diarize": false,
  "file": "string",
  "language": "string",
  "model": "string",
  "prompt": "string",
  "response_format": {},
  "stream": false,
  "temperature": 0,
  "timestamp_granularities": [
    "segment"
  ]
}