This is just a casual 5 minutes project that apply the state-of-the-art language processing model developed by OpenAI, GPT-3 on a Python based voice assistant.
Before beginning, it is advisable for you to create a virtual environment on your device with tools like Anaconda.
conda env create -f environment.yml
conda activate GPT3_VA
This library allows the program to perform speech recognition, with support for several engines and APIs, online and offline
pip install SpeechRecognition
This library allows the program to perform text-to-speech conversion library in Python.
pip install pyttsx3
IF you're on Linux machine, please also install this Multi-lingual software speech synthesizer
sudo apt-get install libespeak-dev
Sign up and Login to your OpenAI account.
Once Login, view your API keys on the top right corner.
Create a new API key if you haven't already
Copy the API key
Paste the API key in the GPT3_VA.py file
python3 GPT3_VA.py