- Trained on 5 min of singing data
- Vocoder: Hifigan
- Pitch extractor: rmvpe
- Embedder: contentvec
- Pretrain: Ov2 Super (40k)
- Batch size: 4

Additional Details:

Tags: RVC v2, Japanese, Fictional Character

Related URL: https://drive.google.com/file/d/1T0naWLkL_xWnlqlc-pkVVBxPHJNcGdAA/view?usp=drive_link

Download Link: https://drive.google.com/file/d/1T0naWLkL_xWnlqlc-pkVVBxPHJNcGdAA/view?usp=drive_link Hosted on Google Drive

Convert this model in EasyAIVoice

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age

young adult

middle aged adult

teenage

Music use

producer tag

rap

music

Style/timbre

anime

villain

cute

Use case

character

game

social

Sample deck

Lean and sweet spot

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

top 4.94 · avg 3.65

female

13

male

5

female base · pitch 0 Quality Score 3.93 · heard as female

Autorun

Run

male

-16 1.54 -12 2.10 -8 4.00 -4 4.27 0 2.94 4 4.80 8 4.01 12 4.90 16 4.94

female

-16 3.05 -12 2.83 -8 3.99 -4 4.16 0 3.93 4 4.43 8 4.04 12 2.91 16 2.83

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...