This is just an idea but i want some suggestion that how can i start doing it
#) thinking of using node as a language
#) Using speech to text api for send my command to llm and vice versa
Hello Lalit, you had the same idea than me, i think could be so much fun.
im doing it in python, started last week, i imported gTTS from google and speech_recognition libraries and with so few lines what it does right now is asking by text for a question, then user answers by microphone, and program answers with voice (it creates an mp3 file that is played instantly for the user).
Would love to know what you make, cheers!