32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #32902 · Canonical Slug /model/1I7igeRrmoQ
RVC v2
· 900 Epochs
Haruka Kiritani
ACT2 · Project Sekai
RVC v2
900 Epochs
Peak Quality 4.86 MOS
Added Nov 8, 2025
★ 6 saved
https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/haruka_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 +16 st (4.86 MOS)
Female Ref
-16
2.3
-12
3.3
-8
3.7
-4
3.3
0
4.6
+4
3.0
+8
3.8
+12
3.7
+16
3.0
Male Ref
-16
2.6
-12
3.7
-8
3.8
-4
4.2
0
4.2
+4
4.2
+8
4.3
+12
4.7
+16
4.9
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Haruka Kiritani (ACT2) (Project Sekai) (RVC v2) - 900 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 Haruka Kiritani
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · +4 st
4.58 MOS
HF
Kohaku
Melty Blood: Type Lumina/Tsukihime: A Piece of Blue Glass Moon
Similar vocal texture
FEMALE · 0 st
4.56 MOS
HF
FEMALE · +4 st
4.53 MOS
HF
FEMALE · +4 st
4.50 MOS
HF
FEMALE · 0 st
3.39 MOS
HF
FEMALE · 0 st
4.53 MOS
HF
Model Documentation & Notes
About Haruka Kiritani (ACT2) (Project Sekai) (RVC v2) - 900 Epochs
this character is featured in project sekai.
trained on 1 minute of audio data from the "a miku who can't sing" movie
(5.1 + revive 3e + bs frazer/becruily karaoke + anvuew mono de-reverb + dialogue isolate (for the singing bit of the dataset), resampled to 40k)
CV: Mayu Yoshioka
pitch extraction: rmvpe
steps: 10.8k
batch size: 2
pretrain: klm 4 hfg / 40k
huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/haruka_act2.zip
Provenance & Open Access
Catalog ID: #32902
Weights Host: Hugging Face
Archive Size: 56.7 MB