Your project reminds me of something I built a while ago using Pollination.ai for images, Gemini Flash for script / captions / inserting transitions and all other editing, Google Cloud TTS for narration/voice, and FFmpeg drive by flash, back then Gemini Flash 2.5 (free) is what i used for these experiments. The result looked like this:

https://www.youtube.com/shorts/IhGR8AC3a_g

Uploaded on sep 24, 2024.

I wasn't happy with how it turned out, so after making 3–4 videos I dropped the idea.

Later, I came across several different video styles that consistently kept me watching. That's when I realized what my videos were missing they simply didn't have the same ability to capture and hold attention.

But i never managed to generate those styles after dozens of attempts and gave up.