32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #32817 · Canonical Slug /model/1H7UYbfcdUw
RVC v2
· 350 Epochs
Kaneko Lumi
ACT2 · Phase Connect
RVC v2
350 Epochs
Peak Quality 4.97 MOS
Added Oct 2, 2025
★ 2 saved
https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/lumi_act2.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 0 st (4.97 MOS)
Female Ref
-16
4.6
-12
4.7
-8
4.4
-4
4.5
0
4.7
+4
4.7
+8
4.4
+12
3.6
+16
2.9
Male Ref
-16
4.4
-12
4.6
-8
4.6
-4
4.8
0
5.0
+4
4.8
+8
4.0
+12
4.3
+16
4.7
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Kaneko Lumi (ACT2) (Phase Connect) (RVC v2) - 350 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 Kaneko Lumi
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · 0 st
4.65 MOS
HF
Cony
Aki Kanada · LINE TOWN
Similar vocal texture
FEMALE · 0 st
4.62 MOS
HF
FEMALE · 0 st
4.71 MOS
HF
Bot
Inanimate Insanity Invitational
Similar vocal texture
FEMALE · 0 st
4.24 MOS
Drive
FEMALE · 0 st
4.72 MOS
HF
FEMALE · 0 st
3.60 MOS
HF
Model Documentation & Notes
About Kaneko Lumi (ACT2) (Phase Connect) (RVC v2) - 350 Epochs
since the lumi model i made a year ago is starting to get stale, i decided to make a new one since she (allegedly) got a new recording setup.
trained on (almost) 16 minutes of audio data from her recent invaderversary stream
(mel-roformer fv7z + bs roformer resurrection (in some areas) + anvuew's room de-reverb + dialogue isolate (in some areas) + slight eq + de-click + de-plosive, resampled to 32k)
pitch extraction: rmvpe
steps: 18.9k
batch size: 7
pretrain: klm 4 hfg / 32k
act1: <#1249666913756381257>
huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/lumi_act2.zip
Provenance & Open Access
Catalog ID: #32817
Weights Host: Hugging Face
Archive Size: 194.8 MB