This must be insanely difficult to get right. I was not expecting such an impressive result from a site that looks so vibe coded! The look is underselling how good this is.
Looks perfectly functional and clear to the eyes for me. They also included a warning to not background/unfocus the tab on a mobile device so that our generation job (on the cloud AFAICT) doesnt get cancelled.
From what I can tell, it used 5.3 hours of single voice fine-tune data.