Easiest way would be finding content on here with audio and movement that you like and running a slideshow over it. A photo program like IrfanView has a lot of slideshow settings. If you want the slideshow as a video, just screen capture it. I think Nvidia and AMD both have solutions for this. There are likely solutions to save file space to accomplish this, but it’s not my wheelhouse.
If you wanted to generate your own audio based scripts, here is a link to some resources. Better solutions may exist, but this is what I found from a quick search.