Name: John Lennon (Talking) | AI RVC Model
Brand: Weights
Rating: 4.6 (7 reviews)

WebKit

 Introducing our latest Retrieval-Based Voice Conversion (RVC) Model, the "John Lennon (Talking) (RVC V2)", trained on a high-quality 32 minute 48kHz dataset using advanced Root Mean Square Variance Propagation Error (RMVPE) techniques. This sophisticated AI voice model captures the iconic sound and speaking style of legendary musician John Lennon, allowing you to generate incredibly realistic text-to-speech outputs.

Our dedicated team has meticulously crafted this model over 380 epochs to ensure exceptional accuracy and authenticity. With its impressive capabilities, the "John Lennon (Talking) (RVC V2)" can be seamlessly integrated into your projects requiring AI music solutions or creating AI covers of John Lennon's famous works.

Unlock limitless possibilities and enhance your creative experience by harnessing the power of the "John Lennon (Talking) (RVC V2)" for your next project. Explore our cutting-edge, user-friendly free AI tools at Weights today and start generating your own AI covers and text-to-speech content with unpre

Trained on a 32 min 48khz dataset with RMVPE. Dataset made by there is also an alternative version on the repo. (Re-upload) Model: Samples:

John Lennon (Talking)

John Lennon (Talking) (RVC V2) 380 Epochs

.albinator

Trained on a 32 min 48khz dataset with RMVPE. Dataset made by There is also a alternative version on the repo.

Retrained on KLM 4 HIFIGAN, 8 Batch Size with a 40khz dataset. I got the dataset from @SpectiZ but i cleaned it more myself. But it was a great help nonetheless since it saved a lot of time, so thank you. Old version here: weights.com/models/cm7b28l6k00036z1wdow5j8vy

John Lennon (1970-1971 Raw Mixes) [KLM4]

Trained on KLM 4 HIFIGAN, 8 Batch Size with a 48khz, 41 min dataset. Feel free to tag me on YouTube @Albinator_ so i can hear the stuff that you make 🙂

Paul McCartney (1990s)

Paul McCartney (1990s) 420 Epochs

Lower the pitch to like -12 for normal voices. Trained on RVMPE Titan, 8 Batch Size with a 40khz, 9 min dataset from the blu-ray. Feel free to tag me on YouTube @Albinator_ so i can hear the stuff that you make.

Count Orlok (2024 Nosferatu Remake)

Trained on RVMPE Titan, 8 Batch Size with a 40khz dataset. I got the dataset from @SpectiZ but i cleaned it more myself. But it was a great help nonetheless since it saved a lot of time, so thank you. New version here:

John Lennon (1970-1971 Raw Mixes) [Titan]

Trained on a 10 minutes & 35 seconds 40khz lossless dataset with RMVPE-Titan with batch size 8. There are more epochs to download if you want that. Model: More stuff: Dataset Sources: A Hard Day's Night Movie (30 Seconds with Adobe Podcast) Help Movie (21 Seconds with Adobe Podcast) Magical Mystery Tour Movie (11 seconds) Live at BBC Albums (1,12 Minutes) Christmas Albums (2,32 minutes) Bootlegs (5,47 minutes) It's not necessary but feel free to tag me on YouTube @Albinator_ so i can hear the stuff that you make

John Lennon (Talking)

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