Introducing the narpy (streamer) RVC v2 350 Epochs model, perfect for creating AI music and covers! This model was trained using 9 minutes of high-quality audio data from a Twitch stream, with a sample rate of 48k. It's part of our RVC series of AI voice models, designed to help you generate unique and engaging content. The model is based on the popular streamer 'narpy', so it's great for generating music in their style. And because it's been trained for 350 epochs, you can expect highly accurate and natural-sounding results. Give it a try and start creating your own AI covers and text-to-speech content today - for free! P.S. Don't forget to check out @iam3m377 on YouTube and give them credit for providing the training data.

Trained using 9 minutes of data from a Twitch vod 48k sample rate, mangio-crepe Please do credit me (@iam3m377 on youtube), I'd love to see what people do with my models

narpy (streamer)

narpy (streamer) RVC v2 350 Epochs

3m377

meatfireexplosion

it a guy who called out konekokitten for wierd thing lol!

speedphantom6481

We making it out of calling out KonekoKitten with this one🗣️🗣️🗣️🗣️🗣️🔥🔥🔥🔥🔥

_dallyp

Trained using around 3 minutes of data gathered from 3 TikTok videos.

Daddy Hagrid (MagicMarbleRace)

Daddy Hagrid (MagicMarbleRace) RVC v2 RMVPE 1000 Epochs

Trained using all the voice lines it has in game (2 minutes of data) 48k sample rate, RMVPE If this is your voice or you know of the original voice wanting it taken down, shoot me a DM. Please credit me (3m377 on Discord or @iam3m377 on YouTube) if you use this model!

SCP 3114 (SCP: Secret Laboratory)

SCP 3114 (SCP: Secret Laboratory) 650 Epochs

Trained using 22 minutes of data. 48k sample rate, rmvpe Please do credit me (@iam3m377 on youtube), I'd love to see what people do with my models

Microsoft Zira TTS

Microsoft Zira TTS (RVC V2) 400 Epochs

Trained using 22 minutes of data. 48k sample rate, rmvpe Please do credit me (@iam3m377 on youtube), I'd love to see what people do with my models it's 150 epochs because it overtrained when i went to 400, and the last backup i had was 150 (i closed the colab before checking)

Microsoft David TTS

Microsoft David TTS (RVC V2) 150 Epochs

Trained using around 10 minutes of data. 48k sample rate, rmvpe This was originally for a commission, but since I couldn't accept their payment method I decided to release the model publicly.

Jessica Chastain

Jessica Chastain (RVC V2) 600 Epochs

FalseEyeD (Vtuber News Anchor)

anon heart

a new version listen do not use these for nefarious reasons

Lyro/jollyrose

Floofphobic

Rainhoe (Vtuber) (RVC v2) 700 Epochs 11.4k Steps: up to 40min of clear audio all sample logs where from videos and streams filtered for clear audio credits to me

Rainhoe 32k Sample

Rainhoe (Vtuber) (RVC v2) 32k Sample

RedVelvety is an American gaming YouTuber who is known for uploading YouTube Shorts with Minecraft footage using the PNGTuber format.

RedVelvety (YouTubers)

AI Bakery

i have no demo of this right now i promise you this works i did this as a request from a friend cause he love her.. do what you wish model:

Shylily

Shylily (VTuber) [275 Epochs, RVC V2]

krasenm

Credit to snuffy for having a really cute voice.

Snuffy

Snuffy (RVCv2, 300 Epochs with 30 mins of data-talking model)

mares_

Created and Trained by me (credits if u use) Link to model:

Tabbes

Tabbes | (RVC V2) - 500 epochs

𝒜𝓁𝑒𝓍 𝑀𝑒𝒽𝒾𝒸𝟣01

If you want to commission an AI model, just DM me. Trained on ~15 mins of talking RVC V2 (500 Epochs) If you use please credit me.

Yuko Yurei - Vtuber

Yuko Yurei - Vtuber - RVC2 500 Epochs.

okay so he was one of the first artists I liked when I first joined twitter and I remembered that he streams on twitch sometimes so I thought why not make a model of him since he sounds like one of the previous admins (rip amplify) also one of squishys friends dopi gave me their dataset of them talking so i just used that as my dataset so im sorry dopi if you ever find this if cake wants me to take down their model, i will do so bleh: <

TheyCallHimCake

TheyCallHimCake (rmvpe) (RVC v2) (1,600 Epochs)

wolfmk

trained on 14 minutes of data (melband roformer + rx10 de-reverb) my 5th vtuber model, wow pitch extraction: rmvpe steps: 15.7k batch size: 7 pretrain: regular v2 huggingface:

narpy (streamer)

Description

Add a comment

FalseEyeD (Vtuber News Anchor)

Lyro/jollyrose

Rainhoe 32k Sample

RedVelvety (YouTubers)

Shylily

Snuffy

Tabbes

Yuko Yurei - Vtuber

TheyCallHimCake

Dizzy Dokuro (Phase Connect / VTuber)

Saiba Momoi (Blue Archive)

Jungkook (BTS)

Takanashi Hoshino (from Blue Archive)

ENHYPEN Heeseung

CaseOh

Villager (Minecraft)

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

Sonic The Hedgehog [Roger Craig Smith]

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Fang [Brawl Stars]

Mortis [Brawl stars]

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

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

Sas (Counter-strike global offensive)

Edgar [Brawl Stars]

SpongeBob SquarePants (Talking And Singing)

Ariana Grande AI

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

Surge (brawl Stars)

Tendou Arisu (Blue Archive)