A Remake of the Google Gemini Fake Demo, Except Using GPT-4 and It's Real

to see the video, go here ->> https://sagittarius.greg.technology/

how to build

clone this repo, cd into it
duplicate .env.example and name the copy .env
fill out the VITE_OPENAI_KEY= value with your OpenAI api key. you must have access to the gpt-4-vision-preview model
then, run:
npm install
npm run dev
the demo will be running at http://localhost:5173

note: the in-browser speech recognition works best in Google Chrome