aisearch-openai-rag-audio
aisearch-openai-rag-audio copied to clipboard
Ability to set threshold, prefix_padding_ms, silence_duration_ms for turn detection
Good Afternoon,
We would like to customize threshold, prefix_padding_ms, silence_duration_ms for turn detection, What would be the best way to achieve this? Thanks
realtime_model = RealtimeModel( modalities=["text", "audio"], instructions="Give brief, concise answers.", voice="alloy", turn_detection=openai.realtime.ServerVadOptions( threshold=0.6, prefix_padding_ms=200, silence_duration_ms=500, ), temperature=0.7, max_output_tokens=1500, )