Name: Raden Juufuutei | AI RVC Model
Brand: Weights
Rating: 4.6 (10 reviews)

 Introducing our cutting-edge AI Voice Model, Raden Juufuutei, powered by Retrieval-Based Voice Conversion (RVC) technology. With its origins from Hololive DEV\_IS, Raden has been trained using 54 seconds of exclusive data, resulting in a highly advanced and specialized voice model. Raden's unique characteristics make it perfect for generating humanlike speech and even creating AI covers of your favorite songs.

The power of RVC allows Raden to understand and mimic various accents, styles, and emotions in spoken language, making it incredibly versatile for text-to-speech applications. Its training also enables it to generate music based on given parameters, adding another layer of creativity when working with audio projects. By utilizing deep learning algorithms, Raden offers natural sounding output without compromising quality or precision.

Discover new possibilities with Weights' innovative solutions! Unlock endless potential as you create AI covers, transform written content into realistic speech, or explore new ways to integrate AI generated music into your creative endeavors - all at your fingertips with our user-friendly free AI tools. Take advantage of the technological advancements brought forth by Weights and join us

Origin: ReGLOSS (Hololive DEV_IS) minutes and 54 seconds of Raden talking Batch size per GPU used during training: 8 Image made courtesy of Won So Credit would be much appreciated if you used this model Discord: or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Raden Juufuutei

AIDontEvenKnow

This audio sample was inferred on the Aesthetic RVC Inferrence Hugging Face Space by r3gm using the RMVPE+ pitch extraction algorithm with "Split Audio" enabled on a minimum value of 96 Hz and a maximum value of 1057 Hz. The audio sample also has the vocal track formant shifted male to female.

Origin: HoloMyth (Hololive English) Trained on: 59 minutes and 57 seconds of Gura talking Save frequency: 1 epoch Log interval: 109 steps Batch size used during training: 16 Sample rate: 32k Learning rate: 1e-4 Image made courtesy of Kurohoshi (@96hoshii_0317) Credit would be much appreciated if you used this model Discord: @AIDontEvenKnow or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely. (Please note this model will be available to use until May 1, 2025, 3 AM PST due to Gura graduating)

Gawr Gura [KLM v4.9]

Gawr Gura [RVC v2] [KLM v4.9] 46 Epochs 5014 Steps

Origin: Rock music Trained on: 48 seconds of Meissner singing: 26 seconds from *Dangerous Games* 22 seconds from *Windows to Light* Save frequency: 10 epochs Log interval: 100 steps Batch size used during training: 3 Sample rate: 32k Image made courtesy of unknown photographer Credit would be much appreciated if you used this model Discord: @AIDontEvenKnow or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Stan Meissner

Stan Meissner [RVC v2] [RMVPE] 210 Epochs 2100 Steps

Origin: Progressive rock music (most notably: King Crimson, U.K. and Asia) Epochs: 670 Steps: 6700 Trained on: 02 minutes and 32 seconds of Wetton singing songs by King Crimson and U.K. from live recordings: * 17 seconds from Starless and Bible Black by King Crimson * 49 seconds from USA by King Crimson * 01 minute and 24 seconds from Night After Night by U.K. Save frequency: 10 epochs Log interval: 100 steps Batch size used during training: 10 Sample rate: 32k Image made courtesy of Mike Inns Credit would be much appreciated if you used this model Discord: @AIDontEvenKnow or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

John Wetton

Origin: HoloMyth (Hololive English) Epochs: 455 Steps: 15925 Trained on: 59 minutes and 55 seconds of Kiara talking Save frequency: 5 epochs Log interval: 175 steps Batch size used during training: 32 Sample rate: 32k Image made courtesy of Kurohoshi (@96hoshii_0317) Credit would be much appreciated if you used this model Discord: @RigidSpinner or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Kiara Takanashi

Origin: Chicago Epochs: 640 Steps: 3200 Trained on: 01 minute and 42 seconds of Lamm singing songs from his solo career and non-Chicago materials: * 46 seconds from Life is Good in My Neighborhood * 46 seconds from In My Head * 04 seconds from Like a Brother by Beckley-Lamm-Wilson * 00 seconds from The Bossa Project * 04 seconds from Robert Lamm Songs: JVE Remixes Save frequency: 40 epochs Log interval: 200 steps Batch size used during training: 8 Sample rate: 32k Image made courtesy of Robert Lamm (note: this image was edited) Credit would be much appreciated if you used this model Discord: @RigidSpinner or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Robert Lamm [1993-2012 Era]

length: 10 mins (talking & singing) Trained using: latest original RVC with some code tweaks and Ov2Super pretrain

Otonose Kanade - Retrained (Hololive), OSuper

Otonose Kanade - Retrained (Hololive) | RVC v2, Ov2Super, RMVPE, 200 Epochs

makidanye

40k rates, 500 epoch the datasets contains 18 minutes of her talking dataset and voice trained by me

Sakura Miko Hololive JP

Sakura Miko Hololive JP (RVC) (500 EPOCHS)

megaaziib

Your Goth Girlfriend that also turns out to be quite the bookworm? Credits: Me (MahdeenSky) Sample:

Shiori Novella

Shiori Novella (RVC 2 | HoloAdvent | Hololive EN 3rd Generation) 430 Epochs

mahdeensky

Gawr Gura

Gawr Gura (Hololive EN) (RVC V2)

dacoolkid44

Since dacoolkid has dominance over most Holo models, I've decided to do one, he hasn't done quite yet, to stay ahead, enjoy Kazama-tais : Me (MahdeenSky) Sample:

Kazama Iroha (HoloX Secret Society | Hololive Gen 6)

Kazama Iroha (HoloX Secret Society | Hololive Gen 6) (RVC 2)

Houshou Marine (Hololive JP)

Houshou Marine (Hololive JP) RVC

Inugami Korone (Hololive Gamers)

yeey5

48k, 600 epochs dataset by me and trained by me V1: kits.ai: Download Link for V2:

Usada Pekora Hololive JP

Usada Pekora Hololive JP (RVC V2) (600 Epochs)

No one made a model (that i know of) of Hajime so i did it myself cause i like her voice and pronunciations

Todoroki Hajime (Hololive DEV_IS) (ReGloss)

thatdudeuzi (DekaiKusa)

Origin: HoloAdvent (Hololive English) Dataset length: 59 minutes and 54 seconds Batch size per GPU used during training: 8 Image made courtesy of kim eb Credit would be much appreciated if you used this model Discord: or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.

Raden Juufuutei

Description

Add a comment

Otonose Kanade - Retrained (Hololive), OSuper

Sakura Miko Hololive JP

Shiori Novella

Gawr Gura

Kazama Iroha (HoloX Secret Society | Hololive Gen 6)

Houshou Marine (Hololive JP)

Inugami Korone (Hololive Gamers)

Usada Pekora Hololive JP

Todoroki Hajime (Hololive DEV_IS) (ReGloss)

Nerissa Ravencroft

Saiba Momoi (Blue Archive)

SpongeBob SquarePants (Talking And Singing)

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

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

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

Mortis [Brawl stars]

Ariana Grande AI

Hu Tao JP (Genshin Impact)

Sas (Counter-strike global offensive)

Villager (Minecraft)

Jungkook (BTS)

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

Tendou Arisu (Blue Archive)

Surge (brawl Stars)

Adel imam (Egyptian Actor) عادل امام (ممثل مصري)

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

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

JENNIE of BLACKPINK [Strong Ver.]