JonathanFly
Feature Request Highly Desirable!
Feature REQUEST is it possible for you guys to also add audio referencing so you cna upload an acapella use the the text to speech tool at the same time to modify lyrics in a sung line there is this other thing called controllable talknet and i was able to do exactly that even tho u have that note contextualize but where does it get the tune of the song from exactly i would like to upload a acapella as a reference audio so your costom made speaker can try to sing over that perfectly and even with added ability to change and the lyrics completely without it damaging the output as the speaker sings perfectly to the uploaded reference acapella files in either .wav or mp3 format please add this feature it would be amazing
Feature REQUEST is it possible for you guys to also add audio referencing so you cna upload an acapella use the the text to speech tool at the same time to modify lyrics in a sung line there is this other thing called controllable talknet and i was able to do exactly that even tho u have that note contextualize but where does it get the tune of the song from exactly i would like to upload a acapella as a reference audio so your costom made speaker can try to sing over that perfectly and even with added ability to change and the lyrics completely without it damaging the output as the speaker sings perfectly to the uploaded reference acapella files in either .wav or mp3 format please add this feature it would be amazing
Bark isn't going to do this out of the box without a lot more work. But I am adding a feature sort to like this. But for music, well, this is what you get. (Bark is part that doesn't like the real one, that is just the input file clip I tried.)
https://github.com/JonathanFly/bark/assets/163408/39a142ff-9242-49ca-9e8d-59a8d703ad37
