Name: ZeroTwo 02 JP Voice (Darling in the FranXX) | AI RVC Model
Brand: Weights
Rating: 4.2 (17 reviews)

WebKit

 Introducing our advanced ZeroTwo 02 JP Voice Model, powered by Retrieval-Based Voice Conversion (RVC) Technology. This cutting-edge AI voice model brings the beloved character from Darling in the FranXX to life through highly realistic and emotive text-to-speech capabilities. With over 370 epochs of refinement, version two delivers exceptional naturalness and accuracy when converting your input into the iconic Japanese tones of Zero Two.

Our ZeroTwo 02 JP Voice Model integrates seamlessly with our proprietary RVC platform allowing users to create AI covers of their favorite songs effortlessly. By leveraging high-quality datasets derived from 20 episodes of the original anime series, we ensure genuine emotion and authenticity within each conversion. Furthermore, utilizing the Mangio-crepe algorithm during pitch extraction ensures optimal performance.

At Weights, we pride ourselves on making state-of-the-art artificial intelligence accessible to all. Don't miss out on creating mesmerizing AI covers using our innovative tools or exploring other exciting possibilities offered by our AI-powered services. Start experimenting today and unlock the full potential of our powerful RVC models –

Dataset From BDMV 20 EP <3 You if credit me :) Using Mangio-crepe in pitch extraction algorithm For Best Result Model : Sample :

ZeroTwo 02 JP Voice (Darling in the FranXX)

ZeroTwo 02 JP Voice (Darling in the FranXX) (RVC V2 370 Epochs)

HoshiSan💫

Here's New Version of My old Chadchart Model with More Clear Audio (RVCv2 mangio-crepe) 185 Epoch Sample :

ชัชชาติ สิทธิพันธุ์ / Chadchart Sittipunt (16th Governor of Bangkok Thailand)

ชัชชาติ สิทธิพันธุ์ / Chadchart Sittipunt (16th Governor of Bangkok Thailand) (RVCv2) 185 Epoch

This Model Train by using 1 minute 15 second Talking Dataset Credit if Use :) Model : Sample :

Amatsuka Uto Talking (JP Vtuber)

Amatsuka Uto Talking (JP Vtuber) (200 Epoch RVCv2 Mango-crepe)

(Same Model as Old AI Hub) Credit if use :) Model : Sample :

Elaina (Majo no Tabitabi)

Elaina (Majo no Tabitabi) RVC V2 200 Epochs

10 second Dataset and Don't Credit Me  Sample Pitch +9 :

Padoru Padoru

Padoru Padoru ( RVCv2 925 Epochs )

Edit : Recommend using Model V2(rmvpe) with Mangio-crepe in pitch extraction algorithm For Best Result (My 6 sample was using rmvpe in pitch extraction) Firstly ~~Idk why its 130 Epochs on 11 minute Dataset.~~ (ok its 370 Epochs on rmvpe) secondly this anime is very hard for me to collect Dataset (I use 20 Episode and that takes a lot of time). I Tried my best :) <3 U if Credit Me (Both is RVCV2) V1 Mangio-crepe e130: V2 rmvpe e370: Note : All of my Model Sample not included effects etc. reverb V1 Sample pitch extraction rmvpe

ZeroTwo 02 JP Voice (Darling in the FranXX)

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