WebKit

Introducing Krasen ME, the latest RVC V2 model trained over 100 epochs at 48K sampling rate. This model is perfect for creating AI music and covers, thanks to its unique voice characteristics derived from a 15-minute dataset. While it has been used primarily for BFDI models so far, its capabilities extend beyond that. Give it a try and discover how you can use Krasen ME to generate text-to-speech outputs like never before!

all ive posted are bfdi models. dunno what else to do.. heres me LMAO 15 min dataset voiced by.. uh who model:

Krasen (ME)

Krasen (ME) | RVC V2, 100 Epochs, 48K

krasenm

Mano Animate

a way better dataset, no longer has that weird "smoothness" and roboticness V1:

BFDI: Blocky

[V2] BFDI: Blocky | RVC V2, RMVPE, 400 Epochs

other model was only rvc 1 and had that instant dataset maker choppiness, so here's my own model

Krasen (ME)

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