Skip to content

Audio

This section lists the implemented endpoints under this capability.

Create transcription

POST /v1/audio/transcriptions

Convert audio into text.

Authentication

  • Bearer Token (Authorization: Bearer <token>)

Request Body

  • Content-Type: multipart/form-data
Field Type Required Description
file string yes Audio file
model string yes -
language string no ISO-639-1 language code
prompt string no -
response_format string no -
temperature number no -
timestamp_granularities array[string] no -

Responses

Status Description Schema
200 Transcription completed successfully AudioTranscriptionResponse

Create translation

POST /v1/audio/translations

Translate audio into English text.

Authentication

  • Bearer Token (Authorization: Bearer <token>)

Request Body

  • Content-Type: multipart/form-data
Field Type Required Description
file string yes -
model string yes -
prompt string no -
response_format string no -
temperature number no -

Responses

Status Description Schema
200 Translation completed successfully AudioTranscriptionResponse

Create speech

POST /v1/audio/speech

Convert text into audio.

Authentication

  • Bearer Token (Authorization: Bearer <token>)

Request Body

  • Content-Type: application/json
  • Schema: SpeechRequest
Field Type Required Description
model string yes -
input string yes Text to convert
voice string yes -
response_format string no -
speed number no -

Responses

Status Description Schema
200 Successfully generated audio string