WebKit

Introducing our improved Half-Life Scientist (RVC v2) model, trained for 800 epochs and generated using advanced AI technology. This new model offers higher quality audio than its predecessor, providing you with superior AI music capabilities. Now compatible with RVC version 2, this updated model also includes an index file for seamless integration into your projects. Our Half-Life Scientist model boasts extensive training on all available data, resulting in over 35 minutes of high-quality audio output. Perfectly suited for creating authentic AI covers, text-to-speech applications, and more. Experience the power of next-generation AI voice models by trying out our free AI tools today.

So I saw someone already did the scientist but it didn't have an index file and was trained on RVC 1. Plus it wasn't trained on all of the available data for the scientist which totals to about 35 minutes. So since nobody's beat me to it yet here it is. Update: the model has been completely retrained due to some issues in the dataset. It should sound a whole lot better now

Half-Life - Scientist

Half-Life - Scientist (RVC v2) (800 epoch)

Big Mitch

funny how i see this model right after playing Half Life for the first time (again)

xhepyxopila

So a little update. After further testing of the model I've determined that this thing needs to be retrained entirely from the ground up

Since there are too many duds in the dataset which makes it sound like shit. Especially when singing

Kaleb Rosenberg

William Afton

Eastern

Harvey Dent

DarkXWolf17

kaben

Made this because I could lol even though there's probably like 3 people that want this me being one of them. Still figured I'll post it. It actually turned out pretty good. Works better at higher pitches but it's pretty versatile since Scotty talks with a ton of emotion. Dataset is comprised of multiple random videos and totals to around 50 minutes.

Scotty Kilmer - YouTuber/Mechanic

Scotty Kilmer - YouTuber/Mechanic (RVMPE) (500 epoch) (RVC V2)

Dataset was about 1:37. I extracted the audio from a hand full of episodes. It's not the highest quality audio unfortunately. I could've gave it more data but that would've taken forever to train.

Jesse (Male) - Minecraft: Story Mode

Jesse (Male) - Minecraft: Story Mode (425 epoch) (RVC V2)

Trained on a 27 minute dataset sourced from Half-Life 2 + Episodes and earlier unused lines from the HL2 beta. Retrained because my last model was crap. This one should be a lot better.

Dr. Kleiner - Half-Life 2

Dr. Kleiner - Half-Life 2 (RVC V2) (RVMPE) (525 epoch)

I am aware that there's already another scientist model on the server but personally I'm not a fan of it. Dataset is 25 minutes. I made another scientist model a while ago but I felt like I could do better so I retrained it on RVMPE. Audio is sourced from Half-Life, Half-Life Opposing Force, Half-Life Blue Shift, Half-Life Decay and Half-Life Uplink. Feel free to use this for whatever you like. Credit would be appreciated.

Half-Life - Scientist (580 epoch) (RVC V2) (RVMPE)

Reuploaded due to failing to delete copyrighted music. Audio sourced from Half-Life 2 and its episodes, Half-Life Alyx, Half-Life 2 beta and any other unused voice lines

Half-Life - Scientist

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