I found the python script below that should be able to give a realistic humanoid voice to chat gpt,converting the text produced by it into a humanoid voice and using my voice with a mic to talk with it. In short terms I want to do the same thing that the “amazon echo / Alexa” voice assistant does,without buying it,but using only what I already have…the Jetson nano (where I have installed ubuntu 20.04). Why the Jetson nano ? Because I can move it from a place to another one within my home,like a voice assistant and because I’ve already spent some money to buy it and I want to use it. This is the video tutorial where I found it :
https://www.youtube.com/watch?v=8z8Cobsvc9k
This is the code connected to the video tutorial :
code.py : https://pastebin.ubuntu.com/p/G4wHRBNr7D/
I have configured my kinect 2 on the jetson nano and I’m using it correctly as a mic to send voice messages to my whatsapp and telegram friends. They can hear my voice very well,so I’m sure that it works. Did that,I have chosen “hw:Sensor” as output device and “hw.Sensor,0” as input device on the qjackctl panel and then I have launched again the python script :
marietto@marietto-nano:/mnt/fisso/Alexa-ChatGPT$# jack_control start
marietto@marietto-nano:/mnt/fisso/Alexa-ChatGPT$# python3 code.py
this is what happens. Everytime I say something (not only genius),these error messages appeared ciclycally :
https://pastebin.ubuntu.com/p/pXY4Ydyncq/
I tried to suppress all that errors modyfing the code with this one :
code2.py : https://pastebin.ubuntu.com/p/m8j2TR4Vqw/
this is what happens when I run it : (sometime I say genius,sometimes not)
https://pastebin.ubuntu.com/p/xZcfMy5cfs/
Goal :
I want to reach the same result reached in this video tutorial :
