← Latest products

We Help Voice AI Handle Group Conversations

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. We built SAA (Selective Auditory Attention) after trying to find ways to make a good experience with multiple robots/multiple agents.

Open source

128 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Boost Your Voice AI Agents with Open-Source Ten VAD

    github.com

    Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

    Hacker News8 pts

  2. Moonshine Open-Weights STT models

    github.com

    higher accuracy than WhisperLargev3

    Hacker News316 pts

  3. Open-source

    github.com

    native audio turn detection model

    Hacker News126 pts

  4. Self-hosted voice AI agent for Asterisk/FreePBX

    github.com

    An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP/Websocket technology https://demo.agent6789.com

    Hacker News32 pts

  5. OfflineTTS

    offlinetts.com

    Free browser-based TTS & STT that runs locally

    Hacker News11 pts