#Vocal interface (alpha)
26 messages Β· Page 1 of 1 (latest)
That is awesome
Care to post the update when done with everything including the raspberry pi
Yes i will π
v1.0 of Neo - Start a conversation by calling him by his name. - Communicate with Neo during a conversation without saying his name. - End a conversation by saying a keyword. - Persistent context during a conversation. (He memorizes the conversation from the beginning) - Context reset when a conversation is over (Allows to limit the cost of using the API)
I am doing the exact same thing with a raspberry pi
Nice, did you plan to use it for automations too ?
Now, and I say this seriously..... update the TTS to sound like Neo (a la Matrix), then we are one step closer to calling the operator and asking for a program on How to fly a Helicopter......... or, Bake a cake π
x) my dream will be true
@valid bobcat
hey do you have the code open sourced?
Not yet
Great π
Thanks
Looks super cool - I want to do something similar. Share what you can.
Yeah, that is exactly what I was looking for... do you have an idea if and when the Raspberry port will be there? π
Could you please share some infos?
I have nothing yet. I have a platform but should start piecing together in a couple of weeks. Will share. Does anyone know what the best open source way to output audio to text is right now using a raspberry pi?
Next chunk text to CHAT.GPT
I will have a mid interface that directs only particular requests to ChatGPT
Can you pass it to whisper than chatgpt and back through tts?
Great Work
I really wanna use it
Iβll release it when I finish it
Any news on it's progress
thatβs awesome, would definitely like to know any updates on itβs release