WebKit

Introducing the HandUnit RVC V2 model, a significant upgrade in AI music and voice generation. This model is specifically trained on the HandUnit dataset from Five Nights at Freddy's: Sister Location and Help Wanted, along with the Curse of Fredbear DLC. With 350 epochs of RVMPE training, it offers enhanced audio quality and clarity compared to its predecessors. It utilizes almost all lines from the mentioned games, resulting in approximately 20-25 minutes of high-quality AI voices. The model also benefits from de-verbing and de-echoing processes, ensuring clear and natural speech output. Start creating your own AI covers or text-to-speech projects using our free AI tools today!

DRIVE - HUGGINGFACE A much higher quality HandUnit Dataset, trained on RVMPE at 350 Epochs. Uses nearly all lines from Sister Location, Help Wanted and Help Wanteds DLC: Curse Of Fredbear Dataset roughly around 20-25 Minutes long. Credit to for helping with de-verbing / de-echoing the dataset, since all his voice lines have echo since theyre played through speakers and such in the games. If used, please just credit my discord :))

HandUnit (FNAF Sister Location / Help Wanted)

HandUnit (FNAF Sister Location / Help Wanted) - RVC V2 - 350 Epochs

kelsoz

AI Hub models do not fall under DMCA, so everyone can have their voices cloned here.

thataiguy

yeah we can TECHNICALLY legally make models of anyone but like

xhepyxopila

my point is i personally respect people not wanting their voice cloned, if they don't want models made of em then we shouldn't make models of em

They should hire us to check for inaccuracies to make sure it's not misused.

"Connection Terminated. I'm sorry to interrupt you Elizabeth, if you still even remember that name"

mares_

viixatakker

Winau 2

I know theres already a BUNCH of Glamrock Freddy models, but some are glitchy and some were trained on -5 Minutes of data Trained on around 25 minutes (RVMPE) I think its very accurate DRIVE - HUGGINGFACE -

Glamrock Freddy (FNAF: Security Breach)

Glamrock Freddy (FNAF: Security Breach) - RVC V2 - 250 Epochs

Drive - HuggingFace Trained on Mangio Crepe, but might redo it and release a Harvest version.

Yung Gravy

Yung Gravy (Rapper) - RVC V2 - 350 Epochs

HuggingFace - Drive This is my updated Poofesure model (Previous 100 Epochs) trained on a slightly longer dataset at much higher Epochs, personally sounds quite accurate to me. If used, please credit :))

Poofesure

Poofesure (YouTuber) - RVC V2 - 300 Epochs

Me Me Big DIsappointment! HuggingFace: Drive: I know theres already a Jacksfilms model made by the wonderful but it was made on a very small, low quality dataset and required some tinkering with pitch to sound OK. This model was trained on around -30 Minutes of Jack using his high quality microphone (Livestreams, Reviews, etc) Examples below. If used, please credit :))

HandUnit (FNAF Sister Location / Help Wanted)

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