32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #32863 · Canonical Slug /model/1HP5XFxXyOo
RVC v2
· 325 Epochs
Nitya Nil
Phase Connect
RVC v2
325 Epochs
Peak Quality 4.75 MOS
Added Oct 28, 2025
https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/nityanil.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 -4 st (4.75 MOS)
Female Ref
-16
4.6
-12
4.6
-8
4.5
-4
4.7
0
4.7
+4
4.6
+8
4.2
+12
3.2
+16
3.0
Male Ref
-16
3.4
-12
4.3
-8
4.6
-4
4.8
0
4.7
+4
4.7
+8
4.4
+12
4.2
+16
4.6
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Nitya Nil (Phase Connect) (RVC v2) - 325 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
41%
Auditory Discovery · Close Alternatives
Voices That Sound Like Nitya Nil
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · +4 st
4.67 MOS
HF
FEMALE · 0 st
4.72 MOS
HF
FEMALE · 0 st
4.64 MOS
HF
Reze
Chainsaw Man:Reze Arc
Similar vocal texture
FEMALE · 0 st
4.53 MOS
HF
FEMALE · 0 st
4.83 MOS
HF
Spinel V2
Steven Universe: The Movie · English
Similar vocal texture
FEMALE · +4 st
4.43 MOS
HF
Model Documentation & Notes
About Nitya Nil (Phase Connect) (RVC v2) - 325 Epochs
she's one of the newer phase connect vtubers from phase saga!
anvuew's room de-reverb model has made the process of making a dataset for this voice model more bearable than it was before bc god damn she has a lot of room reverb.
trained on 15 (and a half) minutes of audio data from the google search checking stream
(voc_fv4 + anvuew's room de-reverb model + dialogue isolate + spectral de-noise + de-click + eq, resampled to 32k)
pitch extraction: rmvpe
steps: 19.8k
batch size: 6
pretrain: klm 4 hfg / 32k
huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/nityanil.zip
Provenance & Open Access
Catalog ID: #32863
Weights Host: Hugging Face
Archive Size: 194.3 MB