Name: Literally Water | AI RVC Model
Brand: Weights
Rating: 4.2 (24 reviews)

 Introducing Literally Water (RVC V2) 300 Epochs, the advanced AI voice model by Weights that harnesses the power of Retrieval-Based Voice Conversion (RVC) technology. Inspired by the soothing sounds of water, this unique model captures the essence of aquatic melodies like no other. Trained over 300 epochs using diverse water audio samples, Literally Water offers unparalleled accuracy and authenticity in its vocal reproduction. Ideal for creating mesmerizing AI music and generating realistic AI covers, it's your go-to tool for innovative sound design and audio generation. With Literally Water, you can explore new creative frontiers and produce stunning results effortlessly. Ready to bring your ideas to life? Sign up now for free at Weights and start crafting extraordinary AI covers and text-to-speech projects today!

Literally Water

Literally Water (RVC V2) 300 Epochs

floatzel

ccateni 28 (Connery Cateni)

A random Fnaf fan

Trained off of EMBRR's *E X T R A* nostalgic series.

Extra Nostalgic

Tord Larsson (Eddsworld)

Tord Larsson (Eddsworld) (RVC V2) 300 Epochs

Audio ReCaptcha

Audio ReCaptcha (RVC V2) 300 Epochs

boykisser

boykisser (RVC v2) 300 epochs

You Are An Idiot

You Are An Idiot (RVC V2) 300 Epochs

I know there was already a Squidward model by , but this one was trained on a much larger dataset of around 30 minutes or longer worth of audio. This model was trained using crepe on the Mangio-RVC fork. As per usual, inferences should work for all RVC forks. This model should be extremely versatile, have fun! ( KEEP SCROLLING FOR MORE DEMOS! )

Squidward Tentacles (SpongeBob)

Squidward Tentacles (SpongeBob) RVC 1.25K Epochs [94K Steps]

ell0er

300 Epochs. Voice clips from Team Sonic Racing and Sonic Twitter Takeover 5 & 7 used to make up this model. If you can it's recommended that it's used with the AI Cover Gen WebUI for male/female pitch adjustment depending on how high pitched or low pitched a song is.

Sonic The Hedgehog [Roger Craig Smith]

A Mii in a Fedora

Literally 20th century fox intro

Literally 20th century fox intro (RVC V2) Epochs 1000

My most ridiculous model yet. Dataset was 1:00 (8.6 seconds repeated). Hurt noises were included, so you will hear hitting noises often.

Villager (From Minecraft)

Villager (From Minecraft) (RVC v2) 500 Epoch

analogspiderweb

Trained on Kendrick's ALL Drake Diss Extraction: RVMPE Sample Rate: 32k Huggingface Download < DM Me for your custom AI commissioned voice models :kittyaww: To Support Me, You Can Donate Here :aismug:

Kendrick Lamar (Drake Diss Era/2024) (TITAN)

Kendrick Lamar (Drake Diss Era/2024) (330 Epochs/8.5K Steps) (TITAN)

gigi_clementine

HATSUNE MIKU V3 UPDATE You must credit if used. Change notes: Added index Trained on Harvest instead of PM Fixed model overall Remember, this post is always updating with updates for this model. See examples and showcases below You must credit if used.

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

FIXED HATSUNE MIKU V3 - VOCALOID (RVC2, 250 epochs) [SCROLL DOWN FOR LINK]

Dataset by me, Trained by me 64 Crepe hop length Trained on 15 mins Dataset, Cleaned and Enhanced Link = Backup Link =

Nicolas Maduro (President of Venezuela)

Nicolas Maduro (President of Venezuela) RVC v2 Crepe 350epochs 20ksteps

Drake

Drake RVC

This is my final SpongeBob model of the main cast (at least for the foreseeable future, I may create a Sandy model eventually). This was trained on over 40 minutes of audio, using songs sang by SpongeBob as well as video game voice clips. This was trained using the crepe method, 64 HOP, on the v2 model architecture and took almost 15 hours to fully train . It should be versatile, however it may favor higher registers. All right, have fun! Oh, and also, IF YOU WANT TO USE THIS MODEL FOR A YT VIDEO OR OTHER SOCIAL MEDIA, YOU MUST PROVIDE CREDIT TO ME IN THE DESCRIPTION!  CHECK OUT THE DEMOS BELOW!

SpongeBob SquarePants

SpongeBob SquarePants {1K Epochs} [99K Steps]

to my knowledge, the other english gumball models posted here were trained on only singing (i think), so i made one trained on both speaking and singing (mostly speaking) trained on a 5 minute dataset from the episodes The Grades, The Diet, & The Faith (rmvpe, 4200 steps) voice actor: Nicolas Cantu transpose works best when between 6-12

Literally Water

Description

Add a comment

Squidward Tentacles (SpongeBob)

Sonic The Hedgehog [Roger Craig Smith]

Literally 20th century fox intro

Villager (From Minecraft)

Kendrick Lamar (Drake Diss Era/2024) (TITAN)

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

Nicolas Maduro (President of Venezuela)

Drake

SpongeBob SquarePants

Gumball Watterson (The Amazing World of Gumball)

Saiba Momoi (Blue Archive)

Jungkook (BTS)

ENHYPEN Heeseung

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

CaseOh

Janet (Brawl Stars)

Cordelius Brawl Stars

Baldi (Baldi's Basics in Education and Learning)

Mortis [Brawl stars]

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

Sonic The Hedgehog [Roger Craig Smith]

Sas (Counter-strike global offensive)

Surge (brawl Stars)

JENNIE of BLACKPINK [Strong Ver.]

Hu Tao JP (Genshin Impact)

Goku (Mario Castañeda) (Latin American Spanish) (UPDATE)

Villager (Minecraft)

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

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

Jay (ENHYPEN)

Tendou Arisu (Blue Archive)

Donald Trump

SpongeBob SquarePants (Talking And Singing)

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

Ariana Grande AI

Fang [Brawl Stars]

Edgar [Brawl Stars]

Sunaokami Shiroko (Blue Archive)

Alastor (Hazbin Hotel/English)