audio

Create transcription (speech-to-text)

Changed on
post/v1/audio/transcriptions

Request

  • Base URL
    http://localhost:8080
  • URL
    http://localhost:8080/v1/audio/transcriptions
  • Auth
    HTTP bearer

Request body multipart/form-data

filestring binary required

Audio file to transcribe

modelstring required

Model ID

languagestring

Input language (ISO-639-1)

promptstring

Optional text to guide the model

response_formatstring

json, text, srt, verbose_json, or vtt

temperaturenumber

Sampling temperature (0-1)

timestamp_granularities[]string[]

Timestamp granularities to populate: word and/or segment

streamboolean

Relay the transcript as server-sent events while the provider produces it

Response

Transcription in the requested response_format: a JSON object for json/verbose_json, a text/plain body for text/srt/vtt, or a text/event-stream when stream=true

object required

Changes

    • info

      added the new optional request property

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: application/json)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: text/plain)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: application/json)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: text/plain)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: application/json)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: text/plain)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: application/json)

    • warning

      added the new internal_error enum value to the / response property for the response status (media type: text/plain)