LAION-AI/natural_voice_assistant

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.

Local voice AI powered by llama-cpp, Kokoro, Nemotron STT, and LiveKit.

Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.

BUDDIE is the first full-stack open-source AI voice interaction solution, providing a complete end-to-end system from hardware design to software applications. Here, you can find a comprehensive solution covering everything from PCB and embedded firmware to the app.

A talking LLM that runs on your own computer without needing the internet.

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.

A simple toy demo of a local voice assistant with whisper and large language model.