Name: Usher [So-Vits 33.6K] | AI RVC Model
Brand: Weights
Rating: 4.4 (18 reviews)

 Introducing the advanced Usher [So-Vits 33.6K] [RVC 1000 UPDATE], an innovative AI Voice Model powered by Retrieval-Based Voice Conversion (RVC) technology. This state-of-the-art model captures the unique vocal characteristics of renowned singer Usher, enabling you to generate remarkably authentic-sounding AI covers and text-to-speech outputs. With its exceptional 33.6K quality and recent RVC 1000 update, the UsherCOMEHU model delivers unparalleled performance in creating AI music and speech.

Developed using a diverse rap dataset, this sophisticated model brings Usher's distinctive style and rhythm into your projects. Ideal for musicians, producers, and developers seeking high-quality AI voices, the Usher [So-Vits 33.6K] [RVC 100

Link [So-Vits-SVC]: < Link [RVC]: < Modelname: UsherCOMEHU (index file added) The dataset included rap acapellas too but i havent test it at all Credits to me

Usher [So-Vits 33.6K]

Usher [So-Vits 33.6K] [RVC 1000 UPDATE]

comehu

Example RVC 600 epoch (mixed version on youtube):

Usher [So-Vits 33.6K] [RVC 1000 Epoch UPDATE]

Example RVC 1000 epoch (isolated acapella btw):

Noxcho 123

New Tinashe model based on BB/Ang3l and Joyride albums. Used more acapellas from Joyride. Used TITAN pretrained model to make this Tinashe model

Tinashe (mainly Joyride era) TITAN MODEL

Retrained Aaliyah model on TITAN pretrain. Includes acapellas from Aaliyah's red album and I Care 4 U this TITAN retrain includes a new acapella "Enough Said" for more accurate low notes interpretation this change also makes the high ends more sharper. Both models rely on isolated acapellas and some official studio acapellas i found and cleaned

Aaliyah (Aaliyah's era) TITAN HQ MODEL

Unserious model i used TITAN pretrained model to make this. I used audio samples from the recreation made by scientists by producing a 3D-printed voice box based on Nesyamun's vocal tract which were really bad and were turned into a meme. Lowering the "Search Feature Ratio" to zero makes the model pronunciate the words a lil more defined by default this model can only produce just one vowel.

Priest Nesyamun (3,000-year-old mummy voice recreation meme)

RVC2 model made using the TITAN Pretrained weights. Presenting my new model of one of my favorites artists Jadiel El Incomparable / El Tsunami. I manually checked the dataset before training and this is the best sounding state i can get at this moment. The dataset is full of isolated vocals made by me Jadiel used to play a lot with vocal harmonies and voice effects so autotunish and vocal doubling should be expected

Jadiel El Incomparable (TITAN PRETRAIN)

to share my first Ov2 model. Brand new dataset with better sounding acapellas which were manually cleaned and checked to give the best result i can for now. This is a remaster of my Aaliyah's Aaliyah model from some weeks ago. I hope you like it Tag me on Youtube @COMEHU so i can hear your creations

Usher [So-Vits 33.6K]

Description

Add a comment

Saiba Momoi (Blue Archive)

Villager (Minecraft)

SpongeBob SquarePants (Talking And Singing)

Miss Circle (Fundamental Paper Education)

Sonic The Hedgehog [Roger Craig Smith]

Takanashi Hoshino (from Blue Archive)

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

Mortis [Brawl stars]

Jungkook (BTS)

ENHYPEN Heeseung

Fang [Brawl Stars]

Jay (ENHYPEN)

Ariana Grande AI

Surge (brawl Stars)

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

Sas (Counter-strike global offensive)

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

FIXED HATSUNE MIKU V3 - VOCALOID [SCROLL DOWN FOR LINK]

CaseOh

Satoru Gojo (JJK) [VA Yuichi Nakamura]