Utilizes the OpenAI API to transcribe an audio file of choice to text, (for use of lecture videos in particular) and then uses some prompt engineering to summarize that text.

To run, install dependencies in requirements.txt, and make an .env file following the .env.example provided you have an API key from OpenAI.

You might also need to sudo install ffmpeg, or manually install it on windows.

Here's a video of the results: