Name: KAKYO YOSARI (AIVOICE) | AI RVC Model
Brand: Weights
Rating: 4.6 (2 reviews)

WebKit

Introducing KAKYO YOSARI (RVC V2), an advanced AI voice model designed by Weights to revolutionize your creative projects. Optimized over 100 epochs using RMVPE and KLM 4.1, this model is best suited for creating realistic AI speech rather than for singing, thanks to its refined and highly nuanced audio extraction techniques. Developed with a 30-minute dataset and a 32k sample rate, it ensures high clarity and engagement in Text-to-Speech applications. KAKYO YOSARI shines in delivering natural conversational tones, making it perfect for content creators and developers seeking to enhance multimedia projects or to create AI covers with incredible precision. Join the AI music revolution now with Weights’ cutting-edge tools to create high-quality, dynamic voiceovers. Explore the possibilities of AI voice modeling today!

hihi !! 30 minutes dataset, 32k w/ batch size 12, aivoice extracted w/ upcon not recommended for singing, use for talking instead. credit as karv4 if you use, or not :p

KAKYO YOSARI (AIVOICE)

karv4x

hai vp: , *Hiyama Kiyoshi* 31 minutes dataset, 48k w/ batch size 8(?, mightve forgot), v2+mve extracted raw data and also exvoice credit as mnkz if you use, or don't <

HIYAMA KIYOTERU (KLM 4.9)

HIYAMA KIYOTERU (RVC V2) (50 Epochs RMVPE) (KLM 4.9)

hihi !! 3 minutes dataset, 32k w/ batch size 8, reuploaded from my other account akdnas;da. credit as karv4x if you use, or not :p

ZORORI (MOTTO! MAJIME NI FUMAJIME KAIKETSU ZORORI)

3 minutes dataset of english dub, 32k w/ batch size 12, sorry for the quality lmfao i don't have netflix credit as karv4 if you use, or not :p

GOSHA (BEASTARS: S3 PART 1 ENGLISH DUB)

GOSHA (BEASTARS: S3 PART 1 ENGLISH DUB) (RVC V2) (250 Epochs RMVPE)

hihi !! 30 minutes dataset, 32k w/ batch size 12, aivoice extracted w/ upcon credit as karv4 if you use, or not :p

UNITY-CHAN (AIVOICE)

SONiKA is a Vocaloid popular for being known as recorded on a Skype call. It uses a ~3 minutes data of renders from Vocaloid4 Editor. I changed her gender parameters so she might sound a bit different. Trained using the new pretrains SimplCup made :3 She is described by Zero-G as a virtual vocalist modeled on the voice of a young girl pop singer. Her Voice provider is unknown Direct download < (also i dont care if my upload templates is different each post LOL)

KAKYO YOSARI (AIVOICE)

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