Name: Vestia Zeta (Hololive ID) | AI RVC Model
Brand: Weights
Rating: 4.2 (70 reviews)

WebKit

 Introducing the Vestia Zeta (Hololive ID) (300 epochs) (Ov2 Pretrain) - an advanced AI Voice Model powered by Retrieval-Based Voice Conversion (RVC) technology. Trained over 300 epochs using the latest RVC v2 and pretrained Ov2 models, this state-of-the-art tool offers highly accurate text-to-speech capabilities, perfect for creating AI covers or generating realistic virtual characters. With its extensive training dataset length of 10 million, it delivers natural, human-like speech, making it ideal for various applications such as voice assistants, gaming avatars, and more. Experience seamless integration and take advantage of Weights' cutting-edge AI tools today! Start creating your own AI covers and transforming your projects with our powerful, easy-to-use solutions – all completely free. Unlock new possibilities and bring your ideas to life with Weights' AI Voice Models.

:firev2: This model was trained on RVC v2 and pretrain Ov2 model (dev-updates: Dataset Length: 10 minutes trained by: Megaaziib Download

Vestia Zeta (Hololive ID)

Vestia Zeta (Hololive ID) (300 epochs) (Ov2 Pretrain)

megaaziib

:firev2: This model was trained on RVC v2 and pretrain Ov2 model (⁠📰┋dev-updates⁠: https://discord.com/channels/1159260121998827560/1159380240271953940/1193957831309799495)
Dataset Length: 10 minutes
trained by: Megaaziib
Download Link: https://huggingface.co/megaaziib/my-rvc-models-collection/resolve/main/zetaTest.zip?download=true

compare to my normal rvc v2, this voice model can go higher note better especially falsetto and less crackling noise when singing, also the quality is slightly better. also better low note voice.

Vestia Zeta (Hololive ID) (RVC V2) (300 epochs) (Ov2 Pretrain)

Fake Teori

Muichiro_Bg

rofinugraha.dev

Hikok Kiko

the audio dataset is 13 minutes of her talking from her freetalk stream using titan medium pretrain dataset sample rate: 32K please credit me if you use it.

Mythia Batford / Indonesian Vtuber [TITAN] (32K)

Mythia Batford / Indonesian Vtuber [TITAN] (RVC V2) (32K) (RMVPE) (300 Epochs)

the dataset is 20 minutes of her singing and talking. dataset created and model trained by me (megaaziib) please credit me if you use it.

Maya Putri (Indonesian Vtuber)

Maya Putri (Indonesian Vtuber) (RVC V2) (300 Epochs) (RMVPE)

dataset and trained by me (megaaziib) please credit me if you use this voice model. the dataset is 20 minutes compilation of her singing acapella on her karaoke streams.

Moona Hoshinova Singing / Hololive ID

Moona Hoshinova Singing / Hololive ID (RVC V2) (300 Epochs)

train and dataset by me (megaaziib) please credit me if you used it. the dataset is from her freetalk streams no nut november video of her singing padoru and her deep voice total dataset around 35 minutes. higher pitch for risu and lower pitch for ayunda voice.

Vestia Zeta (Hololive ID)

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