WebKit

Training data: 3 Doors Down When I'm Gone Bass from Multitrack, with descending copies, each slowed to -3 semitones sequentially from one another. And some extra bass notes thrown in here and there.

Literally Just 3 Doors Down When I'm Gone Bass

ADR3-N

Created this model of Mason to solve the one problem that plagues all RVC models they can't yell, unless ALL of the data is yelling!

Alex Mason (Old VA, Yelling)

Two models a speaking and a shouting model (because RVC struggles to shout!) for Dmitri Belikov as voiced by Mark Ivanir. Made bc MATRVG requested I help dub some CoD content/gameplay!

Dimitri Belikov CoD Cold War

Auto-tune your voice and vocode it into a bassline with this model of a neurofunk bass.

Literally A Neurofunk Bass

Lena Katina model trained on a dataset of studio recordings, lives, and converted acapellas with minimal to no noise, as a companion to my Yulia Volkova model, to test if higher epochs would translate to better quality! I make models on request and process datasets as well. The only caveat is I do pay for Colab, so I rely on donations to keep it affordable, as it is time and resource intensive!

Lena Katina (t.A.T.u.)

Voice model of Yulia Volkova, trained in Colab to 500 epochs, on a dataset of processed studio recordings, speaking, and live, focused on getting her to scream! In higher ranges, at index ratio 1, it seems to be working! This model is a rework of my old models from so-vits and in higher ranges may even be superseded by jpopkaraoke's, for which I (very happily!) provided the dataset. I will be uploading a 500 epoch Lena model as a complement to their 300 epoch model. Using one or both of these Yulia models may be beneficial for different vocal ranges. jpopkaraoke's Yulia/Julia model: Notes, there are some audio that neither of these voice models will be good for converting harsh vocals like Chester Bennington screams etc. Inputting vocals that are screaming can make the pitch dip down instead of interpreting the correct pitch. This is because of the way pitch estimation works in RVC and I haven't found one model or conversion method to combat it. Besides that, there is a delicate balance between getting her to scream and not, and playing with index value 0 and 1 respectively seems to do some kind of magic. Multiple takes may be needed with different index values or even re-singing troublesome parts of acapellas yourself. For my own covers, I re-sing everything multiple times to avoid this. Trying a wide range of index values will give interesting results. Higher index values tend to sound better upon testing, like studio recording, however again, like all other models, your mileage may vary. If you want a screaming model, you may have to try a dataset of harsher vocals! I am willing to do this if anyone asks! I may need to rely on donations at this point to increase my colab subscription though.

Literally Just 3 Doors Down When I'm Gone Bass

Description

Samples

Saiba Momoi (Blue Archive)

Adel imam (Egyptian Actor) عادل امام (ممثل مصري)

JP Furina / Focalors CV: Inori Minase (Genshin Impact)

Ariana Grande AI

Hu Tao JP (Genshin Impact)

JENNIE of BLACKPINK [Strong Ver.]

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

Hatsune Miku

SpongeBob SquarePants (Talking And Singing)

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

Goku (Mario Castañeda) (Latin American Spanish) (UPDATE)

Villager (Minecraft)

Mortis [Brawl stars]

Jungkook (BTS)

Melodie - (Brawl Stars) - (English & Korean Voices)

Tendou Arisu (Blue Archive)

Kanye West