So I have turn_detection enabled with type server_vad. When the AI audio response plays through my speaker, it picks up on my microphone which sends it back to the sevrer so the AI responds to what the AI just previously sent... How do I make it so it ignores its own voice
let sessionUpdateJson: [String: Any] = [
"type": "session.update",
"session": [
"modalities": ["text", "audio"],
"instructions": "MY INSTRUCTIONS",
"voice": "alloy",
"input_audio_transcription": [
"model": "whisper-1"
],
"turn_detection": [ "type": "server_vad" ]
]
]