Mirach Documentation¶
Local-first voice assistant daemon. Press a hotkey, talk, get an answer spoken back — with conversation memory, tool use, and ~3 s round-trip latency.
Quick start¶
What is Mirach?¶
Mirach is a voice assistant that runs as a background daemon on your Linux desktop:
- STT: faster-whisper — Whisper
mediumon GPU, ~0.5 s - LLM: OpenCode CLI — your choice of model with full tool ecosystem
- TTS: Piper — local neural TTS, ~0.3 s
- Control: Single hotkey (default
Alt+Z) for record, process, and interrupt
How it works¶
- Press your hotkey → high beep → start talking
- Press again → low beep → Mirach transcribes, queries the LLM, speaks the answer
- Press during processing → interrupts immediately, starts new recording
Key features¶
- No always-on listening — mic only opens on hotkey
- Session persistence — conversations survive daemon restarts
- Progressive feedback — fillers and notifications during long LLM calls
- User scripts — custom voice-triggered commands without LLM overhead
- Bilingual — English and Spanish UI, triggers, and filler phrases
- Extensible — OpenCode skills for web search, app control, system monitoring, and more
Documentation structure¶
This documentation follows the Diátaxis framework:
| Section | Purpose |
|---|---|
| Tutorial | Learn by doing — install and have your first conversation |
| How-to Guides | Solve specific problems — add scripts, change voices, troubleshoot |
| Reference | Technical details — all configuration options, architecture |
| Explanation | Understand the why — design decisions and tradeoffs |
Requirements¶
- Linux desktop (Wayland or X11 with
notify-send) - Python 3.11+
- NVIDIA GPU with CUDA 12 (CPU mode works with higher latency)
- A microphone
Next steps¶
- Follow the Get Started tutorial to install and configure Mirach
- Read the architecture explanation to understand the design
- Browse the configuration reference to tune every knob
Inspiration¶
This project was inspired by Nate Gentile's video Mi PC Linux ahora trabaja por mí (CachyOS + IA).