Name: Alpha Lexa (Ryans World) - GPT-SoVITS | AI RVC Model
Brand: Weights
Rating: 4.6 (4 reviews)

Introducing the sophisticated AI Voice Model known as "Alpha Lexa (Ryans World) - GPT-SoVITS, 20 Epochs". This revolutionary model leverages sophisticated machine learning techniques to mimic the human voice in a highly realistic manner. This state-of-the-art RVC Model was trained through 20 epochs using the GPT-SoVITS technique and is capable of producing impressively accurate audio imitations. The original dataset hails from the same source used for our ground-breaking RVC models that were crafted in 2023, comprising around four minutes of cleaned voice clips extracted from engaging gaming videos. This advanced model, presented by Weights, excels in generating AI Music - it can produce exquisite AI covers without noise or music interference. Its unrivaled technology allows users to enjoy high-quality and tailor-made Text-to-Speech and AI Covers experiences. Seize the opportunity to leverage our free AI tools to create distinctive AI Covers or generate Text-to-Speech content. Adventure into the realm of AI Music with Weights, and experience the innovation and creativity our advanced technology provides in voice generation.

My first GPT-SoVITs model! It reuses the same dataset from my RVC models of her I made back in 2023 so around 4-ish minutes of voice clips from their gaming videos with music and noise removed as best as possible.

Alpha Lexa (Ryans World) - GPT-SoVITS

Alpha Lexa (Ryans World) - GPT-SoVITS, 20 Epochs

xhepyxopila

The singer from those hilariously bad McDonalds Happy Meal ads from Pakistan. Trained off singing data from the Crash Bandicoot, Sonic, and Play Doh ads minus parts with backing vocals. 500 epochs, RMVPE, TITAN pretrain.

Pakistan McDonalds Ad Singer

Trained off voice lines from Wonder and NSMB U since they were the clearest quality. 300 Epochs, OV2 pretrain.

Kamek (Super Mario Franchise, Wii U / 3DS / Switch Era)

Trained off the uncompressed voice files for Star Fox 64 originally found in the 2020 Nintendo gigaleak. Model uses TITAN pretrain with 300 Epochs. Also I made a mistake and forgot to generate an index before training so uhh, I have no clue if doing it after training makes a difference.

Falco Lombardi (Star Fox)

Haven't tested yet but this should theoretically be my best Birdo model to date. Dataset used is Mario Kart 8 Deluxe BCP since it has her lines in the highest quality DeEcho'd and DeVerb'd so the results aren't weirdly robotic sounding RIN-E3 pretrain and 300 epochs.

Birdo (Super Mario Franchise) - The Final Model

Trained off 2 minutes of data with RIN-3 pretrain

Alpha Lexa (Ryans World) - GPT-SoVITS

Description

Add a comment

Saiba Momoi (Blue Archive)

Jungkook (BTS)

Sonic The Hedgehog [Roger Craig Smith]

ENHYPEN Heeseung

CaseOh

Villager (Minecraft)

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

Ariana Grande AI

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Fang [Brawl Stars]

Mortis [Brawl stars]

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

Takanashi Hoshino (from Blue Archive)

Sas (Counter-strike global offensive)

Edgar [Brawl Stars]

SpongeBob SquarePants (Talking And Singing)

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

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

Surge (brawl Stars)

JENNIE of BLACKPINK [Strong Ver.]