32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #33621 · Canonical Slug /model/1KsftqUpFaj
RVC v2
· RMVPE
· 520 Epochs
Moka Akashiya
RVC v2
RMVPE
520 Epochs
Peak Quality 4.78 MOS
Added Feb 3, 2026
★ 1 saved
https://huggingface.co/Homiebear/MokaAkashiyaTrueForm2026_520e_9360s/resolve/main/MokaAkashiyaTrueForm2026_520e_9360s.zip?download=true
Convert Audio with This Voice in EasyAIVoice
Carries this exact model URL and your selected pitch (0 st ) into the cloud studio.
Zero GPU Setup
🎵 AI Song Cover / Singing
Auto vocal stem separation + instrumental remix
🎙️ Speech, TTS & Voiceover
Convert uploaded voice clip or microphone audio
Audio Decision Loop · Sample Deck
Audition Across 18 Pitch References
Click any semitone cell below to hear how this voice performs on female and male reference vocals and lock your preferred pitch.
★ Sweet Spot: MALE -8 st (4.78 MOS)
Female Ref
-16
4.6
-12
4.5
-8
4.1
-4
4.3
0
4.4
+4
4.2
+8
3.8
+12
2.5
+16
3.2
Male Ref
-16
3.2
-12
4.2
-8
4.8
-4
4.8
0
4.7
+4
4.5
+8
4.6
+12
4.1
+16
3.6
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Moka Akashiya (Rosario + Vampire, Rmvpe) 520 Epochs
CLAP Semantic Analysis · Voice Accords
Sonic Profile at Selected Pitch
Acoustic traits measured directly from the generated output sample. Switch pitches in the Sample Deck to see how timbre shifts.
Auditory Discovery · Close Alternatives
Voices That Sound Like Moka Akashiya
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · 0 st
4.39 MOS
HF
FEMALE · +4 st
4.76 MOS
HF
FEMALE · 0 st
4.67 MOS
HF
FEMALE · 0 st
4.87 MOS
HF
FEMALE · -4 st
4.84 MOS
HF
FEMALE · 0 st
4.21 MOS
Drive
Model Documentation & Notes
About Moka Akashiya (Rosario + Vampire, Rmvpe) 520 Epochs
Download: https://huggingface.co/Homiebear/MokaAkashiyaTrueForm2026_520e_9360s/resolve/main/MokaAkashiyaTrueForm2026_520e_9360s.zip?download=true
-----------------------------------------
Isolated to the best of my abilities, Still noisy but Its an old anime and is just not as easy as you'd expect it to be.
Dataset: 9:14
Sample Rate: 32k
Pretrain: Og Pretrain
Batch size: 8
Made on Kaggle
-----------------------------------------
Credit:
If you use this model please credit me on youtube: @Th4t-Ai-Guy
Provenance & Open Access
Catalog ID: #33621
Weights Host: Hugging Face
Archive Size: 129.3 MB