Mero Takeka - 竹歌メロ (UTAU / DiffSinger) (Japanese + English) [RVC v2] [Crepe] [100 Epochs] [Child Voice] [UTAU→RVC] [ケモノ]

RVC2 model of the UTAU / DiffSinger vocal synth character by DrunkenUTAU; Mero Takeka. Trained using a dataset using his Amber[単独音] and Recanter[rxCVVC] voicebanks as well as his exVOICE-lite library. Mero was voiced by an 8 year old child back in 2012 and has specific restriction and prohibited usage that is available on the huggingface page. Mero was created and managed by アネモネ (Anemone), and. Voice by ♮ / (ℕatural).

Additional Details:

Tags: UTAU, UTAU→RVC, young male, child voice, bright voice, furry, ケモノ, うたけも, furloid, DrunkenUTAU, huggingface, ai-model

Related URL: https://huggingface.co/AnemoneAnEnemy/Mero_RVC2/resolve/main/%E7%AB%B9%E6%AD%8C%E3%83%A1%E3%83%AD%E3%80%90RVC%E3%80%91100%20Epoch.zip?download=true

Download Link: https://huggingface.co/AnemoneAnEnemy/Mero_RVC2/resolve/main/%E7%AB%B9%E6%AD%8C%E3%83%A1%E3%83%AD%E3%80%90RVC%E3%80%91100%20Epoch.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Sample deck

Lean and sweet spot

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

top 4.72 · avg 3.81

female

18

male

0

female base · pitch 0 Quality Score 4.02 · heard as female

Autorun

Run

male

-16 2.97 -12 3.69 -8 4.30 -4 4.72 0 3.10 4 4.23 8 3.49 12 4.37 16 4.05

female

-16 4.04 -12 4.31 -8 4.41 -4 4.06 0 4.02 4 2.88 8 3.90 12 3.51 16 2.49

heard female heard male Quality Score = estimated audio quality, higher is better Ctrl/Cmd-click = select multiple pitches

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age

teenage

young adult

middle aged adult

Music use

music

producer tag

adlibs

Style/timbre

anime

villain

energetic

Use case

assistant agents

game

social

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...