Google Engineers Build Offline AI Translator Using Gemma Model on Raspberry Pi for Under $100

Google built a portable AI translator that works offline, and you can build one too

The code and 3D printing files are available on GitHub, so anyone can build their own AI translator. Google's Gemma models are quite capable, and if you've been wondering exactly how good these models are, there's something you need to see. A team of Google engineers has created a fully offline translator that uses the Gemma 4 E4B model running on a Raspberry Pi 5. The team used Google Antigravity for development and the Gemma 4 E4B model for the AI chops needed to translate different languages. They also designed a 3D-printed housing to fit all the electronics, complete with a display to show the translated text, a mic, a speaker, a push-to-talk button, and a knob to change languages. The team used LiteRT-LM to run the Gemma 4 E4B model and Moonshine text-to-speech to output the translated speech via the speaker. Everything runs on a Raspberry Pi 5, and there's a tiny touchscreen with a custom-built interface to display translations in real time. The best part about the entire project is that it runs entirely offline after the initial setup. So, it can be used anywhere without cellular or Wi-Fi connectivity. It also shows how capable the Gemma 4 E4B model is at handling translations without connecting to a server for extra processing power. Most translation apps, such as Google Translate, require an internet connection to translate speech. The translator is an excellent showcase 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.

Google built an AI translator that runs entirely offline on a Raspberry Pi

Google and Antigravity built an offline AI translator prototype on a Raspberry Pi 5 running Gemma 4 E2B. No internet needed. Open source on GitHub. Not a product announcement. Google and its Antigravity team have built a prototype AI translator that runs entirely offline on a Raspberry Pi 5. The Gemma Translator uses Gemma 4 E2B, the smallest model in Google's open-weight family, to process speech locally without any cloud connection. The device includes a microphone and speaker inside a custom 3D-printed enclosure, creating a self-contained translation device that works anywhere regardless of connectivity. The project is open source on GitHub. Google launched Gemma 4 in April with four model sizes, and the E2B edge variant was specifically designed to run on hardware as small as a Raspberry Pi or Jetson Nano. The Translator prototype is the most tangible demonstration of what that means in practice. Most AI translation tools, including Google Translate, require a cloud connection to process speech. Running everything on-device eliminates that dependency, which matters for travellers in areas with poor connectivity, organisations handling sensitive conversations, and emergency responders operating without infrastructure. This is a technology showcase, not a product announcement. Google has not said it plans to sell the device or integrate it into an existing product. But it points toward a future where AI assistants do not always need data centres to be useful. Antigravity launched as Google's agentic development platform at I/O, and the Translator is one of the first projects built with it that targets non-developers: a physical device that does one thing well, without an internet connection, on hardware that costs under $100. As open models continue to shrink while becoming more capable, devices like this could eventually appear in travel gadgets, accessibility tools, classrooms, or disaster response kits. The Raspberry Pi 5 costs about $80. The Gemma 4 E2B model is free under Apache 2.0. The 3D-printed case and the code are open source. The components for a working offline translator are now available to anyone who wants to build one.

Google Antigravity just built an AI translator that works without the internet

Google has shown off a new AI project that could make language barriers a little less intimidating, and it doesn't need an internet connection to do it. The company has introduced the Gemma Translator, a compact prototype built in collaboration with Antigravity. Unlike most AI translation tools that rely on cloud processing, this device runs entirely offline using Gemma 4 E2B, Google's lightweight open model. Everything happens locally on the device, making it both portable and independent of an internet connection. The prototype is powered by a Raspberry Pi 5 and includes a microphone and speaker inside a custom 3D-printed enclosure, creating a self-contained translator you can carry almost anywhere. AI translation, without the cloud The demonstration shows just how far smaller AI models have come. Instead of depending on remote servers, the Gemma Translator processes speech directly on the Raspberry Pi, translating conversations on-device. That approach offers a few obvious advantages. Travelers could use it in places with unreliable connectivity, while businesses or organizations handling sensitive conversations wouldn't have to send voice data to the cloud. Running everything locally could also reduce latency, making conversations feel more natural. Although Google hasn't positioned the project as a commercial product, it highlights what's now possible with efficient AI models that can operate on affordable hardware. A glimpse of what's coming next The Gemma Translator is more of a technology showcase than a product announcement. Still, it points toward a future where AI assistants don't always need powerful data centers to be useful. As open models continue to shrink while becoming more capable, devices like this could eventually find their way into travel gadgets, accessibility tools, classrooms, or even emergency response kits where internet access isn't guaranteed. For now, Google's latest prototype serves as a reminder that some of AI's most interesting innovations are being squeezed into surprisingly tiny devices that can work almost anywhere.

Google's new offline translator works anywhere -- but you'll have to build it yourself

Will has almost seven years of experience writing about technology and its wider impacts. His work has appeared in The New York Times, BBC News, The Guardian, The Times of London, The Daily Beast, Vice, Slate, Fast Company, The Evening Standard, The i, TechRadar, and Decrypt Media. He has covered everything from crypto scandals to the art world, as well as conspiracy theories, UK politics, and Russia and foreign affairs. Online translation tools have come on leaps and bounds since Google Translate debuted back in 2006. And in recent years, AI models have finally made real-time voice-based translation accurate and smooth. But internet access is never guaranteed, particularly when traveling in foreign lands. Now, Google is test-driving a tool that will allow real-time voice translation without having Wi-Fi or cellular access. The Gemma Translator is effectively just a Raspberry Pi 5, hooked up to a portable mic and speaker. The device runs Google's Gemma 4 E2B, Google's most lightweight and compact large language model. It also features a small touch screen display to display the text being translated, a small knob to cycle through languages, and a push-to-talk button to let the device know when you're speaking. Online translation tools are excellent, so what's the point? The internet isn't everywhere, you know Besides the obvious benefit that you can't rely on connectivity everywhere you go, devices like this could also avoid issues around privacy and data retention. Many companies and regions have strict rules on storing confidential data, uploading to the cloud, or feeding it into AI models. Keeping voice data offline might help avoid these issues. According to Google's announcement, you can select the language you want via the knob, press the button, and the device does the rest. The chassis, which has a distinct vintage look, was entirely 3D printed. Google developers used Antigravity, Google's AI-assisted development environment. You can't buy one -- but you can make your own DIY offline translation for the masses... built with Antigravity Unfortunately, Google hasn't given any indication that it plans to roll it out as a commercial product. But if you're keen, Google has provided the tools to make your own, using a portable PC like a Raspberry Pi. All the files are open-source and available on GitHub, including the STL files you'll need to 3D print the parts. Some companies already offer real-time hardware-based translation tools that work offline, including the Timekettle Fluentalk T1 Pocket Translator, but the key difference is that Google's is open-source and uses cheap and common hardware. This opens the door to creators and start-ups who want to try their hand at making these types of tools. If you think that offline translation could come in handy, but don't want to build or buy your own device, there are also free options available if you don't want to pay for a separate tool. Apple's Translate app allows for offline translation, but you'll need to enable it manually by heading to the Settings tab and downloading the appropriate language pack. The caveat is that Apple warns offline translation may be prone to inaccuracies. Google Translate also provides offline translation if you enable it and download the right packs, but it doesn't support audio at the time of writing; just text and images.