This is impressive, but part of what makes it so is that we are not used to it. As these kinds of AI-generated music/images/videos become ubiquitous, it will be the new normal and they will become less impressive.
Maybe, but I think there is something innately funny about making computers say silly things. As a small child it was peak comedy to me making a Macintosh say “fart” and it’s still funny to me when a computer sings the MIT license.