This is a Next.js project. It's a OpenAI chat UI.
First, run the development server:
npm run dev
# or
yarn next devOpen http://localhost:3000 with your browser to start chatting with openai. You will have to get a apikey from platform.openai.com first. https://platform.openai.com/account/api-keys To apply your openai key, click the config in the UI and apply it.
Updates: The voice over is nearly done, here's one example.
Localhost.3000.-.Google.Chrome.2023-05-30.13-41-01.mp4
In order to use voice over, you will have to run a local tts server. the demo uses a tts server like this.
tts-server --use_cuda true --model_name tts_models/en/jenny/jenny
if you don't have a powerful gpu, you can use the cpu version
tts-server --model_name tts_models/en/jenny/jenny
I use coqui-tts https://github.com/coqui-ai/TTS but it can work with any tts that has a http webapi
Another demo shows stt, using openai whisper running at local computer. sorry for the loud noises, I was using a webcam.