If i set OpenAI realtime model to manage turn detection with semantic VAD and with interrupt response to False, how is it possible that after a speech stopped and before an answer is generated that I receive a new speech detected and speech stopped event?
t
tall-airline-16756
09/17/2025, 4:53 PM
Thanks for reaching out, Sebastián. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
tall-airline-16756
09/17/2025, 4:54 PM
Thanks for reaching out! Could you please let me know if you’re seeing this happen all the time or just in certain situations? Also, are there any custom settings or integrations you’re using that might be affecting how the events are happening? I’m here to help you figure this out!
a
aloof-scooter-47164
09/17/2025, 4:55 PM
sometimes but without any particular pattern. I use the turn detection events from the session to send RPC events to client to notify that the turn changed so user mutes or unmutes
t
tall-airline-16756
09/17/2025, 4:56 PM
I don't have the answer you're looking for.
You could also try asking your question:
• in one of the other Slack channels
or
• to https://deepwiki.com/livekit/livekit_composite which is trained on all LiveKit source code
If you find the answer, please post it here to help others!