A ThreeJS-powered virtual human being that uses a set of neat Azure APIs to do some talking! Added Chat GPT to the mix and maybe you can have for yourself a nice face to chat with. 
demo video: Prompt 3D Demo - YouTube
Repo: GitHub - vaibhav1663/promt3d
demo: https://prompt3d.netlify.app/
That’s an interesting and promising project.
Unfortunately it might be difficult for me to use it. When I gave the prompt “my mouse is not working” the answer appeared in the console, but the character did not say anything, just kept on staring at me. There is indication that the program is still working – maybe it generates the spoken version of the response? I waited for several minutes, but nothing changed. It was still working. When I typed another query, it said “already generating response” and that’s all.
I hope that others will have better a experience than me.
Its working for me.
Working for me, in brave and Chrome both try reloading if it’s showing "already generating response "
if it’s still not working you can try cloning the GitHub frontend and backend repo
PS: change host in the App.jsx file
I was just curious. Consider me as a general user. You should not expect users to clone the repository.
After some more tests, the blocking appears when the reply is long. Short replies (up to a dozen of words) are vocalized within a few seconds. Here is a snapshot with a long reply, shown in the console:
yeah. I also noticed it while development that’s why I trained model to generate concise responses but sometimes it can’t generate small responses. maybe I have to work on this. If you want to work on this feel free to PR on github
Yes, It takes time as I am using a free-tier server for the backend(Yes. I am broke 
). and that’s why it’s not that fast.
I can understand
