development of a personalized dubbing software

Hey guys,
I need a little guidance for this.
I’m exploring the development of a personalized dubbing software using Django for my personal use, inspired by tools like this dubbing (https://wavel.ai/solutions/dubbing) software I’ve been using for quite some time.( I added the link here so that you can take a look at it).
What key tips and considerations would you recommend for someone starting this project? Any insights on speech synthesis technology, UI design, or other aspects would be greatly appreciated!