32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #32541 · Canonical Slug /model/1ER9jCeaNm0
RVC v2
· 350 Epochs
Yurizono Seia
Blue Archive
RVC v2
350 Epochs
Peak Quality 4.40 MOS
Added Jul 9, 2025
★ 10 saved
https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/seia.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 +12 st (4.40 MOS)
Female Ref
-16
-12
-8
-4
0
+4
+8
+12
+16
Male Ref
-16
-12
-8
-4
0
+4
+8
+12
+16
Amber border = Peak NISQA Quality
Raw model title: Yurizono Seia (Blue Archive) (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.
Best Use Case
education and e-learning
14%
Auditory Discovery · Close Alternatives
Voices That Sound Like Yurizono Seia
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · 0 st
3.89 MOS
HF
Hisui
Melty Blood: Type Lumina/Tsukihime: A Piece of Blue Glass Moon
Very close match
FEMALE · 0 st
4.22 MOS
HF
Sparkle
Honkai: Star Rail, Japanese - CV: Reina Ueda
Similar vocal texture
FEMALE · 0 st
4.65 MOS
HF
FEMALE · 0 st
4.71 MOS
HF
Ganyu
Genshin Impact · Japanese
Similar vocal texture
FEMALE · 0 st
4.50 MOS
HF
FEMALE · +4 st
3.49 MOS
HF
Model Documentation & Notes
About Yurizono Seia (Blue Archive) (RVC v2) - 350 Epochs
initially i was going for 475e but then it sounded awful and the 350e version sounded a bit more stable so i went with that.
it's also a test to see how the model trained on klm pretrain would handle lossy audio as dataset
this character's featured in blue archive.
trained on 11 minutes of audio data from both jp and global versions since both of them have different lines. (eq + spectral de-noise)
CV. Tanezaki Atsumi
pitch extraction: mangio-crepe / (applio) crepe - 64 hops
steps: 14k
batch size: 7
pretrain: klm 4 hfg / 40k
hf link: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/seia.zip
Provenance & Open Access
Catalog ID: #32541
Weights Host: Hugging Face
Archive Size: 118.6 MB
