Proof-of-concept for a realtime voice-based mobile OS using the OpenAI Realtime API with WebRTC. It generates the user interface on-the-fly, depending on the task performed by the end user.
Before you begin, you'll need to initialize two .env files, one for the SPA and another for the server. You'll also need an OpenAI API key - create one in the dashboard here:
# SPA env file
cp ./client/.env.example ./client/.env
# Server env file. Paste your OpenAI API key in it
cp .env.example .envIf you want thumbless-os be able to show images, please configure your unsplash access key UNSPLASH_ACCESS_KEY in the .envfile create your account here.
Running this application locally requires Node.js to be installed. Install dependencies for the application with:
npm installStart the application server with:
npm run devThe web application is accessible on http://localhost:3000.
This application uses express to serve the React frontend contained in the /client folder. The server is configured to use vite to build the React frontend.
MIT