Skip to main content
Instead of wiring STT, LLM and TTS separately, you can run the whole turn on one 60db Realtime connection. 60db speaks the OpenAI Realtime GA protocol, so LiveKit’s OpenAI Realtime model works once you point it at 60db. Turn detection, barge-in and function calling run on the 60db server.
1

Install the OpenAI plugin

2

Point RealtimeModel at 60db

agent.py
3

Run the agent

Join the room from the LiveKit Agents Playground and start talking.
With a realtime model, 60db decides turns and interruptions server-side, so LiveKit’s own turn detection and interruption settings on AgentSession don’t apply. Tools you add to your Agent with @function_tool are sent to 60db and run in your agent, as with OpenAI.
Using Pipecat instead of LiveKit? See Pipecat.