🧠🤖

Reachy Mini ER2

Gemini Robotics ER 2 as the embodied brain of your Reachy Mini: it sees, listens, talks and looks around.

reachy_minigemini-robotics-er-2voicevision

How it works

  1. Watch. The robot camera streams about one frame per second to gemini-robotics-er-2-streaming-preview through the Gemini Live API, together with your microphone audio.
  2. Reason. The model answers in short spoken sentences (Gemini TTS on the robot speaker) and decides which body tools to call.
  3. Look. Tools like look_at ask gemini-robotics-er-2-preview to point at the object; the SDK converts the pixel into a head pose.
  4. Express. Nods, dances and emotions come from Pollen's recorded move libraries; face and object tracking keep the head on target.

Two modes

🎙 Voice

Live bidirectional session: talk naturally, interrupt, ask "what am I holding?", "look at the cup", "tell me when I raise my hand".

⌨️ Text

Turn-based chat in the web page: each message ships a fresh camera frame, tools run in a loop, replies can still be spoken.

Tools the model can call

Setup

  1. Install from the Reachy Mini dashboard and start the app.
  2. Open the app page (⚙️ icon in the dashboard, http://localhost:8042 on a Lite).
  3. Paste a Gemini API key (free tier at aistudio.google.com/apikey).
  4. Pick Voice or Text and say hi.