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"
},
}
}