[Short term] Clean up the open source code to make it maximally convenient for new people to get set up and running it.

[pashpashpash]

This is a more general task, but it's important to clean up the code. Right now it's a bit of a mess with python objects being created with unstandardized parameters (for example, the volume object, narration_script, movie_script object, etc. These should likely be classes instead of objects.

The goal here is for the source code to be cleanly organized into understandable, standardized objects/classes/functions so that even people with a limited understanding of code can feel like they can modify the behavior of the code to their liking. This will also help other developers get involved and understand what the code does.

Lastly, the README should be updated to include all of the setup steps, as right now certain things are excluded (i.e. needing to set up torch among other libraries prior to running)

[1ashtray]

I have a list of things that I think should be documented somewhere. I'm not entirely sure where to document this, so I am just commenting it here for now.

1. Make it clear that this does not work for python313 (pytorch is only compatible with 3.12). I am not an experienced programmer, so it took me a while to figure out how to install a lower version of Python into a virtual environment and then how to ensure the correct Python version is being used when running the code.

2. PyMuPDF could not be installed in a Git Bash virtual environment due to an issue with Visual Studio not recognizing a bin folder instead of a Scripts folder. Everything worked fine when the virtual environment was created and managed using PowerShell.

3. The provided ElevenLabs voice key did not work for me. It may be unique for each user or just an issue for those with cheaper subscriptions. I'm not actually sure if this can be fixed in code or if it needs to be documented.

4. cheaper subscriptions for ElevenLabs or ChatGPT requires adjusting settings like semaphore and maximum threads. We could document the recommended values for semaphore and maximum threads based on different subscription tiers. Ideally, the code should default to the lowest settings to avoid errors for users with limited plans.

As an aside, I made my first ever PR, so feel free to provide feedback if there's anything that could be improved.