saa-sdk
attenlabs
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.
Growth over time
5 data points · 2026-07-24 → 2026-09-26How do you feel about this project?
Ask AI about saa-sdk
Question copied to clipboardWhat is the attenlabs/saa-sdk GitHub project? Description: "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.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
How to clone saa-sdk
Clone via HTTPS
Clone via SSH
Download ZIP
Download dev.zipFound an issue?
Report bugs or request features on the saa-sdk issue tracker:
Open GitHub Issues