AI art tools turn text into images. But increasingly, they have been doing way more. I recenty got to try out a tool called Gen 1 by Runway ML and it turns text into video. And if you give it a video reference as well, you can pretty much make it do what you want. The tool is still being tested, so outpits are limited to 3 second clips. But it will obviously open up more soon.
Here is the video I fed it as reference.