This is mainly a toy script so I would recommend created a virtual environment to download the nessary libraries so that your environment dosen't get too messy. you can run "python -m venv foldername" ...

Speech-Recognition-Technology Python offers powerful libraries like SpeechRecognition and PyAudio to implement speech recognition. These tools allow users to convert spoken language into text ...

This allows him to record from the audio playback which provides an internal source for the pyAudio package. His Python script saves snippets of the streaming audio to .wav files.