 Introducing our advanced AI voice model, Benson (600 Epochs) (RVC), powered by Retrieval-Based Voice Conversion (RVC) technology. Trained using 11 minutes of high-quality audio samples, Benson boasts impressive capabilities when it comes to creating realistic and engaging vocal outputs. With its refined tuning across 600 epochs, this model excels at text-to-speech applications, adding depth and personality to your brand's messaging like never before. Furthermore, Benson offers unparalleled versatility in generating AI music covers – simply input a track, and let the model work its magic! To experience these incredible features firsthand, sign up now for access to our FREE AI tools and start crafting customized AI covers and dynamic speech today!

Created by me I put 11 mins samples into it

Benson (Regular Show)

Cracked_Fl

Created by me <@743297533689987082> 
I put 11 mins samples into it

Man i cant write a phrase for the AI to say, how do I do it? 

Nitsuga_kun360 (Nitsuga _kun360)

weird-chairman397

Ayoub Khdahe

ادم mohamed

علي سعد

guntrell

Ring ring, hello what's that, what do you mean they hit the second tower

Lc3ccat

John Legend

John Legend (RVCv2)

TITAN Pretrained 40khz :50 Batch Size: 4 Sample Rate Cutoff 39Khz Clean some songs using Rx11, Plus The Dataset uses least Compressor due to Endless using less Overall compressor and also only song that isn't from Endless is New Slaves Frank Vocals Stem

Frank Ocean Endless Era *Finetune*

Frank Ocean Endless Era  *Finetune*

:59 I know it's not much but it's sounds pretty accurate The Batch Size is set at 2. Pretrain: Original Sample Rate - 40khz and the cutoff is 39 Download

Yellow Pearl From Steven Universe

Yellow Pearl From Steven Universe (RVCv2, RMVPE, And 300 Epochs/5400 Steps)

808s & Heartbreak Studio album by Kanye West All Songs I did on it Total Dataset Time 13:35 (Say You Will✅, Welcome To The Heartbreak❌ ,Heartless✅, Amazing❌ , Love Lockdown❌ Paranoid✅, Robocop✅, Street Lights✅, Bad News❌ See You In My Nightmares✅, Coldest Winter✅, Pinocchio Story❌❌❌) Reason Why I did it because the effects and also no one has done it yet. The pretrain is normal Epochs 375 36K Steps Batch Size 3

Kanye West (808s & Heartbreak Era)

The dataset is from the lossless audio of steven universe soundtrack.

Spinel Steven Universe (48K TITAN)

Mickey Mouse (The Mickey Mouse Clubhouse)

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

freshalicious

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]

ell0er

didn't see any Donald Duck models so decided to take matters into my own hands *(possibly overtrained, not sure.)* 600 Epochs 40k sample rate made with Crepe Link to the model: obligatory Ballin'

Donald Duck

Donald Duck (RVC v2) 600 Epochs

shadowlure

trained at 250 epochs with a 2:48 minute dataset

Skips (Regular Show)

Jacob Wright

Sheen Estevez (Jimmy Neutron)

Sheen Estevez (Jimmy Neutron) RVC v2 Crepe (200 Epochs)

evanthetoonguy40

This model was trained on around 16 minutes of audio using RVC crepe method. It should be pretty good for Hank Hill impressions, haven't tried songs yet, but will post samples soon. Hugging Face Drive

Hank Hill (From King Of The Hill)

Hank Hill (From King Of The Hill) (RVC v2) 750 Epochs

Model: training data was a little rough, so the model can be too. With a little bit of work it can sound quite good though Edit: Going to rewatch the show soon so I can get all of Bill's voice soon, so expect an updated model in a week or two

Bill Cipher

Bill Cipher - RVC v2 (300 Epochs)

Model By Me! Dataset From Warped Kart Racers!

Peter Griffin (Famliy Guy)

Peter Griffin (Famliy Guy) (RVC V2) 300 Epochs

roccoarthurmckay

The model is 48K Hz The step is at 26K and also hop length is set at 60 The dataset is twice as long being 20 minutes and also the Pitch Guidance is set at RVMPE and the season around 1 to 4 (Please Credit Me)

Mordecai (Regular Show)

to my knowledge, the other english gumball models posted here were trained on only singing (i think), so i made one trained on both speaking and singing (mostly speaking) trained on a 5 minute dataset from the episodes The Grades, The Diet, & The Faith (rmvpe, 4200 steps) voice actor: Nicolas Cantu transpose works best when between 6-12

Benson (Regular Show)

Description

Add a comment

Mickey Mouse (The Mickey Mouse Clubhouse)

Mr. Krabs (SpongeBob)

Donald Duck

Skips (Regular Show)

Sheen Estevez (Jimmy Neutron)

Hank Hill (From King Of The Hill)

Bill Cipher

Peter Griffin (Famliy Guy)

Mordecai (Regular Show)

Gumball Watterson (The Amazing World of Gumball)

Saiba Momoi (Blue Archive)

Jungkook (BTS)

Sonic The Hedgehog [Roger Craig Smith]

ENHYPEN Heeseung

CaseOh

Villager (Minecraft)

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

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Fang [Brawl Stars]

Mortis [Brawl stars]

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

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

Sas (Counter-strike global offensive)

Edgar [Brawl Stars]

SpongeBob SquarePants (Talking And Singing)

Ariana Grande AI

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

Surge (brawl Stars)

Tendou Arisu (Blue Archive)