Name: SoraASMR | 32K | AI RVC Model
Brand: Weights
Rating: 4.6 (2 reviews)

WebKit

Discover the soothing and mesmerizing capabilities of "SoraASMR | RVC 2 32K | RMVPE 230 Epochs," an advanced AI voice model expertly crafted by Weights for unrivaled auditory experiences. Embodied within this RVC (Retrieval-Based Voice Conversion) model lies the essence of ASMR excellence, fine-tuned over 230 epochs to ensure ultra-realistic soundscapes and impeccable voice quality. Designed with a sample rate of 32K, SoraASMR delivers crystal-clear audio fidelity, making it a perfect choice for AI music creators and enthusiasts who aspire to produce AI covers with a touch of tranquility.

SoraASMR capitalizes on state-of-the-art preprocessing protocols, including our exclusive "Normal V2" pretraining, to capture the subtle nuances of the human voice. With a modest dataset length of approximately 15 minutes and a batch size of 8, this model distills the essence of an authentic ASMR experience into your AI projects. Whether you're looking to create AI covers that enchant your audience, or you aim to integrate a calming, serene voice into your text-to-speech applications, SoraASMR is poised to elevate your content with its unparalleled auditory charm.

Elevate your audio content with Weights's free AI tools, and immerse your audience in a world of serene sound with "SoraASMR | RVC 2 32K". Start creating AI covers or enhance your text-to-speech applications today - visit our website to explore the possibilities and achieve audio excellence with just a few clicks.

This is a asmr voice of all time. Info: Batch size: 8 Dataset length: ~15 Minutes Sample rate: 32K Pretrain: Normal V2 Please credit me if used :3 Download

SoraASMR | 32K

SoraASMR | RVC 2 32K | RMVPE 230 Epochs

razeristaken

Leo_Frixi

mares_

realpikachuwu

Alex Hayden

Troll model. Info Batch Size: 8 - Dataset Length: 20 min - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

River | troll model

River | 130 Epochs | RMVPE | troll model

High pitched voice models are something. Info Batch Size: 8 - Dataset Length: 1 Hour - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

Lazuli

Lazuli | 150 Epochs | RMVPE

Washed up e-girl turned Vtuber. Info Batch Size: 8 - Dataset Length: 1 Hour - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

Kara Wilderwood

Kara Wilderwood | 198 Epochs | RMVPE

First male voice in how long? Probably to long. Info Batch Size: 8 - Dataset Length: 44 Minutes - Pretrain: Default - Sample Rate: 32k *Please credit me if used *

Alex O'Connor

Alex O'Connor | 244 Epochs | Rmvpe

So i tried out the Ranger optimizer with 5e-5 lr for the gen. Info Batch Size: 8 - Dataset Length: 50 Minutes - Pretrain: Default - Sample Rate: 32K *Please credit me if used *

SoraASMR | 32K

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