I grabbed 2 minutes of clean audio clips from episodes of the anime and trained it on Google colab for 250 epochs.

Tip: Raise the transpose number and pitch for better accurate results, for a male to male voice around +12 - +18 is accurate.

Additional Details:

Tags: Game Freak, Nintendo, Anime, huggingface, ai-model

Related URL: https://huggingface.co/Ryanham1lton/Noibat/resolve/main/Noibat.zip?download=true

Download Link: https://huggingface.co/Ryanham1lton/Noibat/resolve/main/Noibat.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

teenage

middle aged adult

elderly

Music use

music

speaking

producer tag

Style/timbre

cute

villain

deep

Use case

game

animation

character

Sample deck

Lean and sweet spot

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

top 4.90 · avg 4.13

female

13

male

5

female base · pitch 0 Quality Score 4.74 · heard as female

Autorun

Run

male

-16 2.35 -12 2.62 -8 3.61 -4 4.65 0 3.95 4 4.85 8 4.55 12 4.85 16 4.90

female

-16 4.65 -12 4.54 -8 4.56 -4 4.64 0 4.74 4 4.09 8 4.27 12 3.46 16 3.14

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...