Hi Blender community,
I’m a beginner working on a Python script to create videos similar to this Instagram video. The idea is to input an Arabic voice-over and automate: - Syncing animated text with the audio (highlighting important words dynamically).
- Generating or using images to match the voice-over content.
- Possibly turning images (like buildings) into simple 3D models.
- Adding procedural animations and sound design automatically.
I’d love to hear suggestions on the best pipeline to approach this! Tools, add-ons, or libraries that could simplify this process would be really helpful.