Introducing our improved Isabelle Singing model, powered by the RVC v2! With 445 epochs of training, this AI voice generates high-quality AI music covers reminiscent of Animal Crossing. Unlike its predecessor, this version utilizes a superior and more extensive Mangio-Crepe dataset, providing enhanced audio quality compared to the previous Harvest model. If you're looking to create your own AI covers or transform text into speech, try our free AI tools today.

Finally figured out how to use the new collab, so I can make models again This one is a COMPLETLEY redone model of my older Isabelle model cause I personally think it sucks major ass, uses a better and longer dataset and uses Mangi-Crepe instead of Harvest

Isabelle Singing (Animal Crossing), Retrained

Isabelle Singing (Animal Crossing) - RVC v2, 445 Epochs, Mangio-Crepe, Retrained

xhepyxopila

thealanroblox

ccateni 28 (Connery Cateni)

The singer from those hilariously bad McDonalds Happy Meal ads from Pakistan. Trained off singing data from the Crash Bandicoot, Sonic, and Play Doh ads minus parts with backing vocals. 500 epochs, RMVPE, TITAN pretrain.

Pakistan McDonalds Ad Singer

Trained off voice lines from Wonder and NSMB U since they were the clearest quality. 300 Epochs, OV2 pretrain.

Kamek (Super Mario Franchise, Wii U / 3DS / Switch Era)

Trained off the uncompressed voice files for Star Fox 64 originally found in the 2020 Nintendo gigaleak. Model uses TITAN pretrain with 300 Epochs. Also I made a mistake and forgot to generate an index before training so uhh, I have no clue if doing it after training makes a difference.

Falco Lombardi (Star Fox)

Haven't tested yet but this should theoretically be my best Birdo model to date. Dataset used is Mario Kart 8 Deluxe BCP since it has her lines in the highest quality DeEcho'd and DeVerb'd so the results aren't weirdly robotic sounding RIN-E3 pretrain and 300 epochs.

Birdo (Super Mario Franchise) - The Final Model

Trained off 2 minutes of data with RIN-3 pretrain

Brian Griffin (Family Guy)

Approximately 3 minutes of data used Sampled from Mario Party 8 and 10, Mario Kart 8, and Mario Golf: Star Rush Credit me as Frog101 if used in videos or something of the like Mario model by

Princess Peach (Samantha Kelly)

Princess Peach (Samantha Kelly) (RVC V2) 500 Epochs

_frog101_

This is my first model trained using the RVC v2 model arch. Should be fairly versatile. Took around 9 hours to train. Trained on a dataset of around a little less than 30 minutes of video game voice lines from Plankton's character. Hugging Face Link (Mirror): Google Drive OUT THE DEMOS BELOW!

Plankton (SpongeBob)

Plankton (SpongeBob) (RVC v2) 1K Epochs 69K Steps

ell0er

V3 is out on my profile! Gave this model a remake to make sound less robotic and gave it more data. This ain't pilot Charlie so chill with the Verbalase jokes e.e Interested in commissioning high quality models? Feel free to visit my shop!

Charlie Morningstar (OLD MODEL) (Hazbin Hotel)

scruffygamer (RVC Commissions)

:30 Mins used Trained by: Me (Crepe used) case you're going to use it, i will just ask you to give me credits. My Youtube Channel:

Loona (Helluva Boss)

Loona (Helluva Boss) (RVC V2 - 400 Epochs)

Leo_Frixi

This model was trained on the few Clancy Brown video game voice lines I could find. In total it is roughly around 10 minutes or so of audio. It was trained using the crepe method on RVC. Should work well with vocal impressions and possibly singing, but has yet to be tested. Hugging Face Mirror:

Mr. Krabs (SpongeBob)

Mr. Krabs (SpongeBob) RVC 1.25K Epochs [56.25K Steps]

He doesn't poyo anymore, He talk and sing!  Trained by me Drive

Kirby

Kirby (300 Epochs) (RVC V2)

Gabriel (UltraKIll)

Gabriel (UltraKIll) (RVMPE 40k) (250 epochs)

Th4t-Ai-Guy

Rainbow Dash

Rainbow Dash (RMVPE) (Ov2 RVC2 220 Epochs)

Mickey Mouse (The Mickey Mouse Clubhouse)

Mickey Mouse (The Mickey Mouse Clubhouse) (RVC v2) 300 epochs

freshalicious

This model was trained using the crepe method using 25 minutes worth of video game voice lines from various SpongeBob games. The model should be pretty versatile, however higher registers may not work as well due to the deepness of Patrick's voice. This took around 8 hours or so to train. Well anyway, have fun with the model! CHECK OUT THE DEMOS BELOW!

Isabelle Singing (Animal Crossing), Retrained

Description

Add a comment

Princess Peach (Samantha Kelly)

Plankton (SpongeBob)

Charlie Morningstar (OLD MODEL) (Hazbin Hotel)

Loona (Helluva Boss)

Mr. Krabs (SpongeBob)

Kirby

Gabriel (UltraKIll)

Rainbow Dash

Mickey Mouse (The Mickey Mouse Clubhouse)

Patrick Star (SpongeBob)

Saiba Momoi (Blue Archive)

Jungkook (BTS)

ENHYPEN Heeseung

Sas (Counter-strike global offensive)

Fang [Brawl Stars]

JENNIE of BLACKPINK [Strong Ver.]

Sunaokami Shiroko (Blue Archive)

Baldi (Baldi's Basics in Education and Learning)

Mortis [Brawl stars]

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

Sonic The Hedgehog [Roger Craig Smith]

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

Surge (brawl Stars)

Janet (Brawl Stars)

Hu Tao JP (Genshin Impact)

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

Villager (Minecraft)

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

Ariana Grande AI

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Jay (ENHYPEN)

Tendou Arisu (Blue Archive)

Donald Trump

SpongeBob SquarePants (Talking And Singing)

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

Takanashi Hoshino (from Blue Archive)

CaseOh

Edgar [Brawl Stars]

Cordelius Brawl Stars

Alastor (Hazbin Hotel/English)