Background
Most digital services for older people rely on screens and buttons. Many users struggle with screens but can speak and listen. That was the starting point for Diana.
I built Diana as a proof of concept for a partner working in elderly care. The idea was an AI on a tablet that speaks Danish and remembers who it is talking to. The user meets a conversation instead of buttons and menus.
What I built
Diana is a React app that uses Google’s Gemini Live API for real-time voice conversation. The care staff’s instructions to Diana were written with help from Claude. The user speaks, and Diana listens and responds with a warm, patient voice in Danish.
Tech stack
- React + TypeScript frontend optimized for tablets
- Gemini Live API for real-time voice AI with Danish language support
- Express for secure token handling (API key never exposed)
- Zustand for memory between conversations
- Docker + nginx for deployment
Care staff can customize Diana’s personality and knowledge about each resident through settings. Diana never gives medical advice, never corrects memories, and speaks in short, clear sentences.
Results
Diana is a proof of concept. It made it possible to test whether a Danish voice conversation could work as an interface for people who struggle with screens before anyone committed to building a full product.