Konata Izumi (Lucky Star-EN) [300 Epochs, RVC v2]

Created: January 13, 2026
Konata Izumi (Lucky Star-EN) [300 Epochs, RVC v2]

Hello. In case you may not recognize me, I previously went under the name, Felix the Cat, or Felix the Cat by Weights. I used to upload AI voice models of the N.W.A members. I stopped making models in August because of personal life and AI voice model making burnout. Over this course of time, I have ended up developing a small liking towards Lucky Star and the Wu-Tang Clan. Hopefully, over the course of this year, I am gonna make voice models for the entire Wu-Tang Clan. However, I gotta get back to how this works. Because RVC Disconnected, which is what I always used is now end of support, I have to resort to Applio. However, now I finally have a phone number to verify the Lightning AI, so now I can hopefully make longer, maybe even more better AI models.

Stats:
Epoch Count: 300
RVC version: Version 2
Pretrain: I couldn't even know, but when I was training, it said something about Hi-Fi Gan, so that may have something to do with it.
Extraction Type: RMVPE
Dataset Length: 16 Minutes 12 Seconds
Target Sample Rate: 32kHz
English VA: Wendee Lee

DL: https://huggingface.co/CRoyce/Models_I_make/resolve/main/KonataIzumi.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/CRoyce/Models_I_make/resolve/main/KonataIzumi.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age
young adult
middle aged adult
child
Music use
background music
speaking
rap
Style/timbre
warm
cute
villain
Use case
game
social
conversational
Sample deck

Lean and sweet spot

Pick a pitch, compare the Quality Score, then Run. Hold Ctrl or Cmd to select multiple pitches.

top 4.74 路 avg 3.84
female
18
male
0
female base 路 pitch 0 Quality Score 4.11 路 heard as female
Run
male
female
heard female heard male Quality Score = estimated audio quality, higher is better Ctrl/Cmd-click = select multiple pitches
Similar voices

This voice model sounds like

Nearby voices from generated samples. Pick a pitch in the Sample Deck to refresh the matches.

Finding nearby voices for this pitch...