Reachy Mini for Home Assistant

What's inside

Complete voice assistant for your robot

Seamlessly integrates Reachy Mini with Home Assistant via ESPHome protocol.

🎤

Voice Wake

Say "Okay Nabu" to activate. Enable continuous conversation mode for hands-free multi-turn dialogs.

🏠

Smart Home Control

Home Assistant processes your voice commands and controls your smart home devices automatically.

👀

Face Tracking

YOLO-based face detection enables Reachy Mini to look at you during conversations.

😊

Expressive Motion

Automatic emotional feedback with head movements and antenna animations while listening and responding.

📹

Camera Streaming

MJPEG video stream available in Home Assistant as a Generic Camera for real-time monitoring.

🔊

Sendspin Audio

Multi-room audio support via Sendspin protocol. Sync playback with other speakers in your home.

Installation

Up and running in minutes

1️⃣ Open Reachy Mini Dashboard → Applications
2️⃣ Check "Show community apps" checkbox
3️⃣ Find "Reachy Mini for Home Assistant" and click Install
4️⃣ Home Assistant auto-discovers via mDNS

Usage

Start talking to your smart home

Once installed, Home Assistant will automatically discover your Reachy Mini. Say "Okay Nabu", then speak your command like "turn on the lights" or "what's the temperature?" Enable "Continuous Conversation" switch for multi-turn dialogs.

ESPHome protocol Auto discovery 30+ entities Continuous conversation

What's new

Changelog

v0.5.16

2026-01-11

Remove: Tap-to-wake feature (too many false triggers)
New: Continuous Conversation switch in Home Assistant
Refactor: Simplified satellite.py and voice_assistant.py

v0.5.15

2026-01-11

New: Audio settings persistence (AGC, Noise Suppression, Tap Sensitivity)
Refactor: Move Sendspin mDNS discovery to zeroconf.py for better code organization
Fix: Tap detection not re-enabled during emotion playback in conversation

v0.5.14

2026-01-11

Fix: Skip ALL wake word processing when pipeline is active (prevents false triggers)
Fix: Eliminate race condition in pipeline state during continuous conversation
Improve: Control loop increased to 100Hz (daemon updated)

v0.5.13

2026-01-10

New: JSON-driven animation system for conversation states
New: AnimationPlayer class inspired by SimpleDances project
Refactor: Replace SpeechSwayGenerator and BreathingAnimation with unified animation system

v0.5.12

2026-01-10