I played around with this a while back and there are Vim plugins for it. My biggest problem was having to compile the thing from source which involved also compiling a custom version of LLVM, which took forever. It's possible this is no longer a problem.

I'm aware of extempore; it's impressive. I actually use SuperCollider quite a lot (in vim), which is not lispy (more OO) but in a similar space. But what I want is something that can operate on music how vim operates on text, not just operating on music-written-as-text in vim!