when it comes to deep learning style vocal synths vs concatenative synthesis style vocal synths i like and use both, theres pros and cons for each, i adore deep learning synths for their versatility in vocal modes/expressions/appends/whatever and their breaths and of course im a fan of how many have multi-lingual functionality, but one thing they just cant beat concatenative on is the late 2000s-ass NND-ass doujin-ass impossibly fast rapid fire syllable'd japanese pop singing a la disappearance of hatsune miku. to be honest miku barely handles it. thats what the song is about. to me no one does it better than a basic but well oto'd CV utau LOL
0 notes