MIDIs, audio conversion, and speech synthesis! 
I’d suggest this tool for MIDIs, though, because audio conversion can only handle a few seconds, but if you want more detail you can use a speech synthesizer like SAMMY or SAM!
Quarantined ramblings on the difference between SAMMY and SAM
- SAM takes up a significant amount of space in your project because it has to store a large dictionary in the game, whereas SAMMY’s is stored on the website.
- On the other hand, SAM works entirely within makecode whereas SAMMY requires a website and a lot more work to translate the message into phonetics.
- SAM can convert a set of 300 english words; SAMMY is entirely custom, so it can convert any sound, word, or language.
- They sound different; SAMMY is fluid whereas SAM is segmented. One or another may sound more realistic to you, it’s up to personal preference!
- Both of them require you to show the spoken text on screen to make the illusion of speech work.