I understand you're looking to implement wake word detection with LiveKit. While LiveKit doesn't have a built-in wake word detection engine, you can definitely achieve this with some external integrations and custom handlers. Here are a couple of friendly options to consider: • Wake Word Handler: You might want to try the WakeWordHandler from the agent-demos repository. It works alongside the VoicePipelineAgent and can detect wake words in real-time audio streams, which is pretty handy! • Custom Implementation: Another approach is to build a custom agent using Speech-to-Text (STT) services like Deepgram or Gladia to spot specific keywords. There are some great examples in the python-agents-examples repository that might inspire you. Keep in mind, these methods do involve integrating STT services and setting up voice activity detection (VAD) to get the best accuracy. If you'd like, I'm here to help guide you through the setup or answer any questions along the way! Sources: Voice activity detection (VAD) parameters | LiveKit Docs | README.md | home_assistant/homeautomation.py | livekit-plugins/livekit-plugins-deepgram/livekit/plugins/deepgram/stt.py | Turn detection and interruptions | LiveKit Docs