Description
Created by me, this voice is perfect for speaking roles and somewhat good for singing, 9mins of audio used with little to no static in the background. Discord is my absolute favorite character, so obviously it's the first thing I wanted to try and do when making AI models! Make sure to mess around with the input pitch because that drastically changes how he sounds and makes him sound more accurate.
Comments
Duet of my and nicegames AI Transpose -7 for Discord and 0 for Fluttershy
Discord singing by himself
if you dont have discord sing discord we will riot
this acapella is godly
i've been waiting for someone to make this model
i tried
Did you only train this on kids.AI or did you also do this locally Or with colab?
Kits and Colab, both use the same audio but the Colab version sounds better imo, it's my first model so there's definitely more I could do in the future and I will update it whenever I learn more and improve :)
Based. At least we have more proof that Kits isn't good especially without index.
Yeah, Kits struggles a lot more with voices and singing in general, though it is helpful for people who don't know how to use RVC models at least. Fun to play with but not the best
i was waiting too and i couldn't stand waiting LMAO
So I learned it in one day and tried
Discord (John De Lancie, My Little Pony, MLP) RVC v2 Crepe & Kits.ai (500 Epochs)
he sounds so good in this
Add a comment
Samples
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch
Weekly Metrics
Users also tried
More to explore
Loading more