32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #33346 · Canonical Slug /model/1K3BBMOSjew
RVC v2
· 650 Epochs
Still In Love
Singing v2 · Umamusume
RVC v2
650 Epochs
Peak Quality 4.98 MOS
Added Jan 19, 2026
★ 9 saved
https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/stillinlove_sing_v2.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: MALE +8 st (4.98 MOS)
Female Ref
-16
4.3
-12
4.5
-8
3.3
-4
4.1
0
4.0
+4
3.8
+8
3.9
+12
3.0
+16
2.6
Male Ref
-16
1.5
-12
3.6
-8
4.4
-4
4.8
0
4.9
+4
4.9
+8
5.0
+12
4.9
+16
4.9
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Still In Love (Singing v2) (Umamusume) (RVC v2) - 650 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 Still In Love
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · 0 st
4.26 MOS
HF
Noel
Melty Blood: Type Lumina/Tsukihime: A Piece of Blue Glass Moon
Similar vocal texture
FEMALE · 0 st
4.88 MOS
HF
FEMALE · 0 st
4.38 MOS
HF
FEMALE · 0 st
4.23 MOS
HF
Yuri Sakazaki
Kaori Horie · The King of Fighters & Art Of Fighting
Similar vocal texture
FEMALE · 0 st
4.35 MOS
Drive
Ugallu
Machikado Mazoku 2-choume
Similar vocal texture
FEMALE · 0 st
4.29 MOS
HF
Model Documentation & Notes
About Still In Love (Singing v2) (Umamusume) (RVC v2) - 650 Epochs
-# i added more data to the dataset bc i felt like the model didn't sound good enough
this character's featured in umamusume (both the anime and game)
trained on 10 minutes of of her singing data extracted from the game
(cleaned using anvuew's de-reverb, uvr de-echo (in some parts), resampled to 40k)
***songs used:***
- umapyoi legend
- brilliant phantasia
- make debut!
- ms. victoria
- uma summer
- meni shuki rush-sshu!
-
**CV:** Saki Miyashita
-
pitch extraction: rmvpe
steps: 25.3k
batch size: 6
pretrain: klm 4 hfg / 40k
hf: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/stillinlove_sing_v2.zip
Provenance & Open Access
Catalog ID: #33346
Weights Host: Hugging Face
Archive Size: 142.6 MB