Name: Otonose Kanade - Retrained (Hololive), OSuper | AI RVC Model
Brand: Weights
Rating: 4.8 (22 reviews)

 Introducing the Otonose Kanade - Retrained (Hololive) model, an advanced AI voice model powered by Retrieval-Based Voice Conversion (RVC) technology version 2, and enhanced with Ov2Super and RMVPE. This state-of-the-art model has undergone rigorous training, including 200 epochs, resulting in highly accurate text-to-speech capabilities and impressive AI music generation abilities. With its ability to sing and talk, it's perfect for creating realistic AI covers of your favorite songs. At Weights, we offer cutting-edge AI tools, including our RVC model, for you to explore and harness the power of artificial intelligence. Try out our free AI tools today to create professional-sounding AI covers and transform your text into speech.

length: 10 mins (talking & singing) Trained using: latest original RVC with some code tweaks and Ov2Super pretrain

Otonose Kanade - Retrained (Hololive), OSuper

Otonose Kanade - Retrained (Hololive) | RVC v2, Ov2Super, RMVPE, 200 Epochs

makidanye

you should add it with youi's singing it could help if possible

Velvet

using: RVC Disconnected Dataset length: 13 mins (talking singing rapping) Pretrain & sample rate: TITAN Medium 32k F0 method: rmvpe Batch size: 8 Note: feel free to use for voice changer but I'd advise against posting AI covers or any content/streams using her voice in YouTube Twitch Tiktok etc. until I get a chance to ask her for permission.

Elia Stellaria (EN VTuber), TITAN Medium

Elia Stellaria (EN VTuber) | RVC v2, 280 Epochs, TITAN Medium

using: Applio 3.1.1 Dataset length: 8 mins (talking) Pretrain & sample rate: TITAN Medium 32k F0 method: Crepe (8 hop length) Batch size: 8 Note: she can sing and play violin (not related to this talking model). No singing vocal and violin model at this moment tho.

Amahane Miran - Talking, TITAN Medium

Amahane Miran (VSinger) - Talking | RVC v2, 230 Epochs, TITAN Medium

using: Applio 3.1.1 Dataset length: 5 mins (talking) Pretrain & sample rate: TITAN Medium 32k F0 method: Crepe (8 hop length) Batch size: 8

Usada Pekora (Hololive), TITAN Medium

Usada Pekora (Hololive) | RVC v2, 241 Epochs, TITAN Medium

using: RVC Disconnected Dataset length: 15 mins (talking) Pretrain & sample rate: Original 32k F0 method: RMVPE Batch size: 8

Tokino Sora (Hololive)

Tokino Sora (Hololive) | RVC v2, 210 Epochs

length: 9.5 mins (English talking with some Japanese dialect) Trained using: RVC Disconnected (Ov2Super pretrain) Note: Speaks Japanese natively but also speaks English fluently in Kansai accent.

Nina Momose, OSuper

Nina Momose (VTuber) | RVC v2, Ov2Super, RMVPE, 250 Epochs

40k rates 500 epoch the datasets contains 18 minutes of her talking dataset and voice trained by me

Otonose Kanade - Retrained (Hololive), OSuper

Description

Add a comment

Sakura Miko Hololive JP

Hoshimachi Suisei (Hololive JP)

Tokoyami Towa (Hololive JP)

Elizabeth Rose Bloodflame

Takanashi Kiara

Saiba Momoi (Blue Archive)

Villager (Minecraft)

Sas (Counter-strike global offensive)

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

Fang [Brawl Stars]

Jay (ENHYPEN)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Mortis [Brawl stars]

Jungkook (BTS)

ENHYPEN Heeseung

Sonic The Hedgehog [Roger Craig Smith]

CaseOh

Takanashi Hoshino (from Blue Archive)

Surge (brawl Stars)

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

SpongeBob SquarePants (Talking And Singing)

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

Miss Circle (Fundamental Paper Education)

Ariana Grande AI

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