I am building a automation where the user can input a pdf document and then it extracts the text and gives them an Video Overview (Just like in NotebookLM).
Any suggestions on How to use it?
I researched alot but was only able to find out tools like HeyGen which only provides AI avatars.
The problem is Most of these tools don't give API access to specific tools.
Would really mean a lot to me for your suggestions.