Reachy Mini
OpenWebUI managed voice and personality · No wake word

Local Conversation App

Run Reachy Mini conversations on your own stack.

An OpenWebUI-first, camera-aware companion for Reachy Mini. Use OpenWebUI workspaces/models for personality and voice behavior, with VAD listening without a wake word.

OpenWebUI model dropdown OpenWebUI-managed TTS No-wake-word VAD Workspace-managed personalities
Reachy Mini dancing

Reachy Mini can move, dance, and emote while holding a natural conversation.

What’s inside

All-in-one conversational layer for your robot

The app blends local speech, vision, and motion so Reachy Mini feels present.

🎤

Natural voice chat

Talk freely and get replies from your configured local chat-completions model.

🎥

Vision-aware replies

Ask the camera tool to see what’s in front, track a face, or keep attention on whoever is speaking.

💃

Expressive motion

Queue dances, play recorded emotions while Reachy listens and talks.

🧠

Personalities on demand

Switch conversation styles in OpenWebUI workspaces/models while the bot exposes tools like dance, camera, and tracking.

🌐

Ready for your setup

Works with wired or wireless Reachy Mini, and can run vision locally or through the default cloud model.

How it feels

From hello to helpful in seconds

  • 👋 Say “Hey Reachy” and start chatting—no extra setup in the moment.
  • 👀 Ask what it sees; it can peek through the camera or keep focus on your face.
  • 🎭 Trigger emotions or dance breaks to keep the conversation lively.
  • 📝 Follow along with live transcripts in the web UI or run audio-only from the console.

Where it shines

Great for demos, teaching, and playful exploration

Show off how Reachy Mini listens, responds, and moves in sync. Whether you’re guiding a class, hosting a booth, or experimenting at home, the app keeps the robot expressive without juggling scripts or joystick controls.

Live conversation Face tracking Camera tool Dance library Profiles & tools