YOOOOOOOO we’re Gonna have VOICE soooon…

So I Made a HUGE improvement in the Code with Almost EVERYTHING complete.

So Basically I plan on having 4 Layers of the project :

1st Layer : Takes the User Input and writes a FULL script on how to explain that thing. Returns a JSON with things like Section, the Narration, what the Animation should Look like.

2nd Layer : Takes the Narration Script and Uses a Local TTS Model to get that. and Get this Its supported in like 100+ Languages

3rd Layer : This is Where I am RN will take in how the animation should look like and will output a MANIM code.

So this is the plan for Now, drop a MSG if y got any ideas!!