AudioAIExplainer

This project aims to provide an intuitive introduction to the audio AI space as it exists in August 2025. I place a great deal of emphasis on the "intuitive" part; please do not rely on this document to be literally and precisely correct in every respect.

A large amount of this document was generated in collaboration with commercially available LLM models; when I didn't know things I asked Gemini questions, and when I needed help making a GIF I asked ChatGPT for python code. If this offends you this is probably not the doc for you. Any code used to generate media is available at the associated github repo