AryanEmbered

Why not an open implementation like directml?

1

Also why not stream the responses to the model as they come instead of waiting for the entire response before tts starts?

Adjusting for ambient Noise missing.

4

You might want to add this line after with sr.Microphone as source `r.adjust_for_ambient_noise(source, duration = 1)` Wasn't recording for me till I added this. Windows btw.

Hey, what license are you going to put on this? I'd like to steal.. Ahm, get inspired by this to build my own. I would really like to know what...