Users browsing this thread: 1 Guest(s)
Turning voices into TTS?
#1
I like sentence splicing like in Gmod videos, but unless I have a list of what files say what, so it's easier to find the syllables I want, I have a difficult time of splicing sounds together.

I wonder if there's an "automated" way of doing this, not necessarily to instantly recognise syllables, but to at least organize them for the user to sort out by phoneme and intensity/emotion. That way, when someone types up a sentence, the sounds are automatically assigned to different words and can be further edited from there (changing the accent of a word, increase or decrease intensity, etc.).

I know UTAloids have the capacity to do this for music, but I've not much success in navigating UTAU.
Smug Collector and Creator of the Extraordinary! Wink
Reply
Thanked by:


Forum Jump: