Transcription config for `gpt-4o-mini-transcribe` doesn't work?

Looks like the documentation is not up-to-date.
Right now you actually have to use the “session” field to work or it will throw an error

{
  "type": "transcription_session.update",
  "session": {
    "input_audio_format": "pcm16",
    "input_audio_transcription": {"model": "gpt-4o-mini-transcribe"},
    "turn_detection": {
      "type": "server_vad",
      "threshold": 0.5,
      "prefix_padding_ms": 300,
      "silence_duration_ms": 500,
    },
    "input_audio_noise_reduction": {
      "type": "near_field"
    },
  }
}
1 Like