32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #33328 · Canonical Slug /model/1JYiW3vHsL6
RVC v2
· 1000 Epochs
Ugallu
Machikado Mazoku 2-choume
RVC v2
1000 Epochs
Peak Quality 4.29 MOS
Added Jan 16, 2026
https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/ugallu.zip
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: FEMALE -4 st (4.29 MOS)
Female Ref
-16
2.6
-12
2.3
-8
4.1
-4
4.3
0
4.3
+4
4.0
+8
4.2
+12
3.5
+16
2.9
Male Ref
-16
1.4
-12
1.6
-8
3.3
-4
3.5
0
3.4
+4
4.2
+8
2.9
+12
2.9
+16
4.0
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Ugallu (Machikado Mazoku 2-choume) (RVC v2) - 1000 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 Ugallu
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
Yuki Suou
Playful · Alya Sometimes Hides Her Feelings In Russian
Very close match
FEMALE · 0 st
4.60 MOS
HF
FEMALE · 0 st
4.20 MOS
HF
Yuki Suou
Alya Sometimes Hides Her Feelings In Russian
Similar vocal texture
FEMALE · 0 st
4.54 MOS
HF
FEMALE · 0 st
4.91 MOS
HF
FEMALE · 0 st
4.74 MOS
HF
FEMALE · +4 st
4.66 MOS
HF
Model Documentation & Notes
About Ugallu (Machikado Mazoku 2-choume) (RVC v2) - 1000 Epochs
-# a bonus model for the "machikado rvc model collection"
this character's featured in machikado mazoku 2-choume.
trained on 2:47 minutes of her speaking from season 2
(cleaned using mel deux, anvuew karaoke (in some parts), anvuew de-reverb, resampled to 40k)
-
**CV:** Fairouz Ai
-
pitch extraction: rmvpe
steps: 18k
batch size: 4
pretrain: legacy core v1.5 / 40k
hf: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/ugallu.zip
Provenance & Open Access
Catalog ID: #33328
Weights Host: Hugging Face
Archive Size: 74.5 MB