Run a Local Real-time Voice AI Assistant in a Single Docker Container

tom_doerr · x · 2026-08-13

Developer ShayneP open-sourced the local-voice-ai project on GitHub, featuring a fully local real-time voice AI assistant.

The project integrates STT, LLM, and TTS within a single Docker container, managed by a unified Python supervisor process. It relies on LiveKit Agents for real-time communication, uses llama.cpp to run a local LLM (defaulting to the Gemma 4 E2B quantized model), and integrates Nemotron STT and Kokoro TTS. The project aims to enable anyone to easily build a powerful, privacy-preserving local voice agent.

Original post →

More from coding & agent

coding & agent channel →