Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.
real-time twilio webrtc realtime openai speech-processing voice-assistant ai-agents conversational-ai voice-activity-detection voice-ai voice-sdk livekit elevenlabs pipecat voice-agents barge-in addressee-detection device-directed-speech selective-auditory-attention
-
Updated
Jul 15, 2026 - Python