Any AI software to recommend if I wanna add in picture/video based on the VO of a person speaks?

Example: The person told a story about a person sat and waiting for someone. Then I want this imagination that the picture/video contains someone (3D or cartoon) is sitting and waiting someone.

Edit:
Found a powerful one.

Closed

This post has been edited by Sunshape: Jan 21 2025, 10:38 PM