Name: Some Anime Girl, [SOVITS] | AI RVC Model
Brand: Weights
Rating: 4.4 (5 reviews)

WebKit

Introducing "Some Anime Girl," a captivating AI Voice Model from Weights that harnesses the power of innovative RVC (Retrieval-Based Voice Conversion) technology. This model is a marvel of AI Music, designed specifically for anime enthusiasts and creators who are eager to venture into the realm of virtual vocalization. Crafted through meticulous training, the model has undergone 10 epochs with GPT and 8 epochs with So-Vits, ensuring an authentic and emotive audio experience.

Boasting dual-language capabilities, "Some Anime Girl" excels in both English and Japanese, delivering its best performance in Japanese, as evidenced by extensive testing. The model's versatility makes it perfect for developers and artists seeking to create AI covers or integrate unique voiceovers into their projects. Its convenience is further highlighted by the inclusion of necessary files, a reference audio for optimal voice conversion, and an infer_config.json file, ready to streamline your creative process.

Elevate your creative works with the enchanting voice of "Some Anime Girl." Whether you're looking to produce AI-powered covers or integrate lifelike Text-to-Speech into your projects, Weights is here to empower your imagination. Start crafting your AI covers or explore the possibilities of Text-to-Speech with our free AI tools today and bring your artistic visions to life.

First take on So-Vits, how was it? I didnt have an idea for a pic so just enjoy a default one lol. Trained using a dataset from Huggingface that I got access to and with some help from the guide since I am very new to this lel. ^^^ The dataset I got access to allows this kind of posting, so I don't need to post a separate zip file with conditions :matsuripray: Im not sure how to format a sovits model post, but repo link is below. It includes The 2 files required. - The infer_config.json file. - The reference audio (can do well without one, but i heard it was recommended to include one). Sample audio is also attached for both English and Japanese. It can work well with Japanese and English, however JP is the best by far after testing.

Some Anime Girl, [SOVITS]

Some Anime Girl (GPT So-Vits, 10 epochs[GPT], 8 epochs[SOVITS]

kidbot

I aint even got an image for this one man what the hell- The original (if you wanna rot your brain) can be found here, however, the clips were taken from a roblox short channel [Bloopo] (I wish i was kidding): Demo audio is attached, use pitch 10 and index 0.2. This was trained locally, and i'm sure as hell not getting that time back :bjahmeltdown:

"We're not done!" Voice, 28 files, TITAN

"We're not done!" Voice, 240 epochs, 28 files, TITAN

"Heya batboy~" ~~as you can tell i am running out of ideas for models-~~ Trained locally. Used a Season 1 video, trimmed, vocal isolated, and split using Cafeteria (dataset HF space). Feel free to react to this with a skull emoji, I wont judge Works at pitch 12 for male, 0 or -1 for female. Model:

Femboy Joker [Darkseptor]

Femboy Joker [Darkseptor] (RVC v2, RMVPE using Titan, 36 files, 240 epochs)

First model trained locally on my RTX 4060, took around 2 hours. Whispering is recommended, but can do talking as well. Original video: Demo attached. Link to model: no credit is required, just enjoy :blue_thumbsup:

Bonk! ASMR

Bonk! ASMR (33 files, DMR, 320 epochs)

You are not immune from propaganda when shes around. Side effects include fever and/or chills, running nose, swirls in eyes, and a decline in gaming skills in extremely rare chances. BTW boycott the Pillsbury dough boy. Used her placid plastic duck video as training data. Use with realtime only, sample attached.

Mallory's Asylum

Mallory's Asylum (120 files, 250 epochs, RMVPE)

Hello Vanguard, it is nice to see you again Trained off the lines in the main game (cannot give because ubisoft would slit my throat) Use pitch 11-13. Works well if you already know how to do somewhat of a female robot voice (if that makes sense lol). Index doesnt matter, but Ive got best results at 0.5-0.6. Realtime only, sample attached. Model:

Some Anime Girl, [SOVITS]

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