Reachy Mini
Voice assistant ยท Smart home ยท Expressive motion

Home Assistant Integration

Your robot, your smart home.

Control your Home Assistant with voice using Reachy Mini robot. Speak naturally, watch it respond with expressive movements, and manage your entire smart home hands-free.

Wake word detection Tap-to-wake Face tracking 30+ HA entities
๐Ÿค–โšก๐Ÿ 

Reachy Mini listens, responds, and controls your smart home through Home Assistant.

What's inside

Complete voice assistant for your robot

Seamlessly integrates Reachy Mini with Home Assistant via ESPHome protocol.

๐ŸŽค

Voice & Tap Wake

Say "Okay Nabu" or tap Reachy Mini's head to activate. Multiple wake options for convenience.

๐Ÿ 

Smart Home Control

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

๐Ÿ‘€

Face Tracking

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

๐Ÿ˜Š

Expressive Motion

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

๐Ÿ“น

Camera Streaming

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

๐Ÿ”Š

Sendspin Audio

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

Installation

Up and running in minutes

  • 1๏ธโƒฃ Open Reachy Mini Dashboard โ†’ Applications
  • 2๏ธโƒฃ Check "Show community apps" checkbox
  • 3๏ธโƒฃ Find "Reachy Mini for Home Assistant" and click Install
  • 4๏ธโƒฃ 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" or tap the robot's head, then speak your command like "turn on the lights" or "what's the temperature?"

ESPHome protocol Auto discovery 30+ entities Continuous conversation

What's new

Changelog

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
  • Remove: Deleted broken hey_reachy wake word model
  • Revert: Default wake word back to "Okay Nabu"
v0.5.11
2026-01-10
  • Fix: Reset feature extractors when switching wake words
  • Fix: Add refractory period after wake word switch
v0.5.10
2026-01-10
  • Fix: Wake word models now have 'id' attribute set correctly
  • Fix: Wake word switching from Home Assistant now works
v0.5.8
2026-01-09
  • Fix: Tap detection waits for emotion playback to complete
  • New: DOA turn-to-sound at wakeup
v0.5.0
2026-01-07
  • Face tracking with adaptive frequency
  • Sendspin multi-room audio integration
  • Optimized shutdown mechanism
View older versions
v0.4.0
2026-01-07
  • Daemon stability fixes
  • Face tracking enabled by default
v0.3.0
2026-01-06
  • Tap sensitivity slider entity
  • Music Assistant compatibility
v0.2.0
2026-01-05
  • Automatic facial expressions
  • Emotion playback integration
v0.1.0
2026-01-04
  • Initial release
  • Voice assistant functionality