It’s a handheld voice translation device that runs its entire AI processing pipeline locally on a Raspberry Pi 5, with no internet required after the initial setup. There’s no cloud to route audio through, no API key to maintain, and no service that can be discontinued. Translation runs on Google’s Gemma 4 E2B model via LiteRT-LM, hitting around six tokens per second on the RPi 5 while using under 1.5GB of RAM. The result is a complete speech-in, speech-out translation loop that stays on the device from start to finish. The fact that none of the audio ever leaves the device is simply a consequence of building something that had to work without one.