Name: Q (Star Trek TNG Audiobook) | AI RVC Model
Brand: Weights
Rating: 4.0 (1 reviews)

WebKit

 Introducing the advanced Q (Star Trek TNG Audiobook) RVC Model v2, meticulously trained over 556 epochs using the Retrieval-based Voice Conversion (RVC) technology. This cutting-edge AI voice model specializes in capturing the essence of the iconic character Q from Star Trek: The Next Generation, delivering astonishingly authentic text-to-speech experiences. Despite its minor drawback in handling breathings effectively, it still excels at providing impressive results for various applications. Transform your audio projects by creating AI covers or utilizing our outstanding text-to-speech functionality with this remarkable RVC Model v2, available through our user-friendly, FREE Weights AI tools. Don't miss out; unleash your creativity today!

RVC: v2 Extraction Type: rmvpe Epochs: 556 : Doesnt handle breathing all that well, presumably due to breaths being mostly removed in the original dataset. Working on additional variants derived from TNG, DS9 and VOY episodes.

Q (Star Trek TNG Audiobook)

Q (Star Trek TNG Audiobook) (RVC v2, 556 Epochs, RMVPE)

phaserflow

**RVC:** v2
**Extraction Type:** rmvpe
**Epochs:** 556
**Link:** https://huggingface.co/PhaserFlow/RVC_Models/resolve/main/STTNG-Q-Audiobook_e556_s67832_RVC_V2_RMVPE.zip
**Note:** Doesn’t handle breathing all that well, presumably due to breaths being mostly removed in the original dataset. Working on additional variants derived from TNG, DS9 and VOY episodes.

MysticonsFan62

RVC: v2 Extraction Type: rmvpe Sample Rate: 40 kHz Epochs: 344 Steps: 28208 Batch Size: 8 Dataset Size: 32m 11s

Coach (Left 4 Dead 2)

Coach (Left 4 Dead 2) (RVC v2, 344 Epochs, RMVPE)

RVC: v2 Extraction Type: rmvpe Sample Rate: 32 kHz Epochs: 452 Steps: 65088 Batch Size: 7 Dataset Size: 56m 52s

Max Caulfield (Life is Strange)

Max Caulfield (Life is Strange) (RVC v2, 452 Epochs, RMVPE)

RVC: v2 Extraction Type: rmvpe Epochs: 388 Sample Rate: 40 kHz Batch Size: 8 Dataset Size: 19m 45s Notes: Dataset was exclusively lines from the second DLC, since they were distributed uncompressed and without effects applied.

Cave Johnson (Portal 2)

Cave Johnson (Portal 2) (RVC v2, 388 Epochs, RMVPE)

RVC: v2 Extraction Type: rmvpe Epochs: 112 Sample Rate: 32 kHz Batch Size: 4 Dataset Size: 10m 05s Notes: Yee-haw.

Victor (Fallout: New Vegas)

Victor (Fallout: New Vegas) (RVC v2, 112 Epochs, RMVPE)

RVC: v2 Extraction Type: rmvpe Epochs: 404 Sample Rate: 32 kHz Batch Size: 4 Dataset Size: 25m 43s Notes: Skyrim voice lines seem to only have 32kHz of actual audio data, and spectral repair sounds like crap to my ear so far, hence the 32kHz sample rate. Speaking sample music is royalty-free, from AudioCoffee:

Q (Star Trek TNG Audiobook)

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