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.
More from coding & agent
- Dev builds MCP server that lets AI agents outsource phone calls to real humans — Many_Benefit_3393 · 2026-10-16
- A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16
- Mergelock: open-source MCP server catches semantic merge conflicts git misses across parallel AI agents — ksadayamuthu · 2026-10-16
- OpenUI 1.0 launches open source, turning agent text answers into live interactive UIs — heyshrutimishra · 2026-10-16
- 10 GitHub repos to see what your AI agent really did, from Langfuse to claude-code-log — victor_explore · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16