Sign in
Realtime

Create transcription session

Create an ephemeral API token for use in client-side applications with the Realtime API specifically for realtime transcriptions. Can be configured with the same session parameters as the transcription_session.update client event.

It responds with a session object, plus a client_secret key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API.

Returns the created Realtime transcription session object, plus an ephemeral key.

post/realtime/transcription_sessions

Request body

input_audio_format'pcm16' | 'g711_ulaw' | 'g711_alaw'

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian byte order.

includestring[]

The set of items to include in the transcription. Current available items are: item.input_audio_transcription.logprobs

Response

Session created successfully.

modalitiesstring[]

The set of modalities the model can respond with. To disable audio, set this to ["text"].

input_audio_formatstring

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

Changes

Changed in 2 of the 31 revisions of this API.39

  • c7549184dd9526See the full diff
    • ●

      added the new gpt-live-transcribe enum value to the input_audio_transcription/model/anyOf[subschema #2]/ response property for the response status 200

      response-property-enum-value-added

    • ●

      added the new gpt-transcribe enum value to the input_audio_transcription/model/anyOf[subschema #2]/ response property for the response status 200

      response-property-enum-value-added

    • ○

      added the new optional request property input_audio_transcription/keywords

      new-optional-request-property

    • ○

      added the new optional request property input_audio_transcription/languages

      new-optional-request-property

    • ○

      added the new gpt-live-transcribe enum value to the request property input_audio_transcription/model/anyOf[subschema #2]/

      request-property-enum-value-added

    • ○

      added the new gpt-transcribe enum value to the request property input_audio_transcription/model/anyOf[subschema #2]/

      request-property-enum-value-added

    • ○

      added the optional property input_audio_transcription/keywords to the response with the 200 status

      response-optional-property-added

    • ○

      added the optional property input_audio_transcription/languages to the response with the 200 status

      response-optional-property-added

    This revision also has 1 change that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 81aa43d6a9f113See the full diff
    • ●

      added the new gpt-realtime-whisper enum value to the input_audio_transcription/model/anyOf[subschema #2]/ response property for the response status 200

      response-property-enum-value-added

    • ○

      added the new optional request property input_audio_transcription/delay

      new-optional-request-property

    • ○

      added the new gpt-realtime-whisper enum value to the request property input_audio_transcription/model/anyOf[subschema #2]/

      request-property-enum-value-added

    • ○

      added the optional property input_audio_transcription/delay to the response with the 200 status

      response-optional-property-added