Google Engineers Build Offline AI Translator for Global Accessibility

A team of Google engineers has developed an offline AI translator using the Gemma 4 E4B model running on a Raspberry Pi 5. The device, which includes a touchscreen display, push-to-talk button, and knob to change languages, is designed for use in areas without cellular or Wi-Fi connectivity.

The project utilizes Google Antigravity for development and the Gemma 4 E4B model for AI capabilities. The team also employed LiteRT-LM to run the Gemma 4 E4B model and Moonshine text-to-speech to output translated speech via a speaker.

One of the standout features of this project is its ability to function entirely offline after initial setup, making it suitable for use in various environments. The device showcases the capabilities of both Google Antigravity and the Gemma 4 models.

All the code and 3D-printing files for the enclosure are available on GitHub for anyone to download, compile, and create their own offline translation device.