transcription_session.updated

Server acknowledgement that transcription_session.update was received and the session was configured successfully.

After this event, the server can accept other client events such as input_audio_buffer.append.

event_idstringrequired

Server-generated unique event identifier

typestringrequired

Fixed value

Possible values: [transcription_session.updated]

session object

Realtime API session metadata (audio format, language, etc.).

input_audio_formatstring

Audio format. For all formats, audio must be 1 channel (mono).

For example, pcm16 is 16-bit PCM audio.

For twilio, you can send audio using the Twilio Media Streams API audio format as-is.

Possible values: [pcm16, float32, twilio]

Default value: pcm16

input_audio_sample_rateinteger

Input audio sample rate

Default value: 24000

input_audio_number_of_channelsinteger

Input audio number of channels

Default value: 1

input_audio_transcription objectrequired

Settings for transcribing input audio.

languagestringnullable

Specify the input audio language using an ISO-639-1 code.

Optional, but specifying it may improve transcription accuracy and/or latency.

Possible values: [en, ja]

target_languagestringrequired

Specify the transcript language using an ISO-639-1 code.

Possible values: [en, ja]

turn_detectionboolean

Whether to enable turn detection. If false, the conversation.item.input_audio_transcription.completed event is not sent.

Default value: false

objectstring

Fixed value

Possible values: [realtime.transcription_session]

transcription_session.updated

{
  "event_id": "string",
  "type": "transcription_session.updated",
  "session": {
    "input_audio_format": "pcm16",
    "input_audio_sample_rate": 24000,
    "input_audio_number_of_channels": 1,
    "input_audio_transcription": {
      "language": "en",
      "target_language": "en"
    },
    "turn_detection": false,
    "object": "realtime.transcription_session"
  }
}