Voice Models v2
EasyAIVoice ↗
32,020 Verified Open Models 28,884 Multi-Pitch Audition Ready 100% Direct Source URLs (HF · Drive · MEGA)
Kyushu Sora
RVC v2 ·390 Epochs

Kyushu Sora

RVC v2 390 Epochs Added Jan 2, 2024
Open Model Weights Vault · Hosted on Hugging Face · 138.3 MB
✓ Verified Direct URL
https://huggingface.co/Kryptone/RVCollection-Revamped/resolve/main/VoiceVoxRVC/KyushuSora.zip?download=true
Download Raw Weights (.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
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.

18 Reference Previews
FEMALE reference · Pitch 0 st
Generated reference preview · Ready to audition
Semitone Shift (`-16` to `+16` st) · Bar height indicates NISQA clarity score
Female Ref
Male Ref
Audible Female Audible Male
Raw model title: Kyushu Sora [Sweet] (VOICEVOX, ~160 files, 390 epochs, RVC v2)
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.

Technical Profile

Architecture: RVC v2 · Training: 390 Epochs · Source Host: Hugging Face

Auditory Discovery · Close Alternatives

Voices That Sound Like Kyushu Sora

Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.

High-clarity female voice
MALE · 0 st 5.13 MOS HF
High-clarity female voice
FEMALE · 0 st 5.12 MOS Direct
High-clarity female voice
FEMALE · 0 st 5.11 MOS HF
Libby Rue Better Nate Than Ever
High-clarity female voice
FEMALE · 0 st 5.10 MOS HF
Gallica Metaphor ReFantazio
High-clarity female voice
FEMALE · 0 st 5.10 MOS HF
High-clarity female voice
MALE · 0 st 5.09 MOS HF
Model Documentation & Notes

About Kyushu Sora [Sweet] (VOICEVOX, ~160 files, 390 epochs, RVC v2)

I plan on making this a full on collection, but this is just a test to see if you guys would want that. Trained on the same way as the other 2. No singing, realtime only. Turn index up to around 0.95 if you want the japanese accent. Use 12 or 13 for male voice, and 0 or -1 for female voice. Samples attached. Model: https://huggingface.co/Kryptone/RVCollection-Revamped/resolve/main/VoiceVoxRVC/KyushuSora.zip?download=true TOS included in zip, please read carefully. I now have a HFSpace where you can make your own datasets, its always getting updated and its pretty fast without a GPU: <https://huggingface.co/spaces/Kryptone/GDMGS>

Provenance & Open Access
Catalog ID:#23331
Weights Host:Hugging Face
Archive Size:138.3 MB
Rights & Safety: Report / Takedown