fluxions-ai/vui

Vui (pronounced "vooey") is a real-time voice assistant you run on your own computer. You speak into a microphone, it transcribes your speech, passes the text to a language model running locally, and streams an audio reply back, all without sending your conversation to a cloud service. The pipeline works in three steps: ASR (automatic speech recognition, converting your voice to text), LLM (a local language model that generates a response), and TTS (text-to-speech, converting the response back into audio). Each step is pluggable, meaning you can swap out different software for each stage. The default speech recognition uses faster-whisper or Moonshine, the language model connects to Ollama or other compatible local LLM software, and the text-to-speech uses Vui Nano, a 300 million parameter model trained on conversational speech that includes natural sounds like breaths and hesitations. Key features include barge-in (interrupt the assistant mid-reply and it stops to listen), voice cloning (upload a sample audio clip to make the assistant sound like a specific voice), persistent memory across sessions, and a set of built-in tools like web search and timers. There is also an optional sidecar process that handles longer tasks like reading email or calendar events. The API is compatible with OpenAI's Realtime API format, so existing apps built for that can point to Vui instead. It runs on a local GPU and is designed for developers who want a self-hosted, privacy-preserving voice assistant they fully control. A one-line installer sets up the full stack. The full README is longer than what was provided.