Name: XXXTENTACION | AI RVC Model
Brand: Weights
Rating: 4.8 (14 reviews)

WebKit

 Introducing the XXXTENTACION (RVC) 150 Epoch - the latest advancement in AI voice modeling from Weights. This cutting-edge model utilizes Retrieval-Based Voice Conversion (RVC) technology to bring you stunningly realistic text-to-speech capabilities, capturing the unique tone, style, and emotion of legendary rapper XXXTENTACION. With 150 epochs of training, this AI voice model delivers unparalleled accuracy and precision, allowing users to generate their own customized AI covers and music tracks. Whether you're looking to create personalized audio messages, innovative new music compositions, or simply explore the boundaries of what's possible with artificial intelligence, the XXXTENTACION (RVC) 150 Epoch offers endless possibilities. Best of all, our user-friendly platform makes it easy to get started - try creating your first AI cover or text-to-speech message today with our free AI tools at weights.ai!

I'll update it when I figure out how to continue after saving a model with RVC LOL But anyway it's trained on about 30 minutes of data, about 25 of those being an interview and 5 being singing The model is better with rapping and talking than singing

XXXTENTACION

XXXTENTACION (RVC) 150 Epoch

shadowtb

Here are two short examples I have on hand, I'll upload more later

I forgot I made this LOL, this is probably a more realistic test of the model

< Sample Rate: 40k Batch Size: 8 minutes Used songs from X and XTENDED, split and cleaned as best as I could

Ken Carson - X/XTENDED

Ken Carson - X/XTENDED (RMVPE, RVC v2, 320 Epochs, OG Pretrain)

8 Batch Size 4 Minutes Dataset RVC V2 Default Pretrain 40K Trained off of acapellas made from the Boy Barbie album, as well as a few leaks from the same time to pad out the already small dataset All his mics and mixes from this time were terrible I'm shocked this model works as well as it does

Ken Carson - Boy Barbie Era

Ken Carson - Boy Barbie Era (RVC V2) (RMVPE) (230 Epochs)

< Trained on 2024, Different Day and Menage.

Playboi Carti - MUSIC Era Baby Voice

Playboi Carti - MUSIC Era Baby Voice (RMVPE) (RVC V2) (750 Epochs)

< Based on the early deep voice sound where it was "faked" using formant shifting Uses Killers (Wicked), Two Out, Mr. Miyagi and Ready To Crash as the dataset, all isolated, cleaned and eq'd for training.

Playboi Carti - MUSIC

Playboi Carti - MUSIC V1 (RMVPE) (RVC V2) (850 Epochs)

Made with acapellas I made for the songs "EVILJ0RDAN" and "BACKR00MS" DO NOT USE THIS IF YOU AREN'T MAKING A SONG/PLAN TO MIX THE VOCALS The demos will show why <

XXXTENTACION

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