Voice Models v2
EasyAIVoice ↗
32,011 Verified Open Models 28,877 Multi-Pitch Audition Ready 100% Direct Source URLs (HF · Drive · MEGA)
Usher
RVC v2 ·550 Epochs

Usher

2023 Voice

RVC v2 550 Epochs Peak Quality 4.66 MOS Added Aug 30, 2023 ★ 1 saved
Open Model Weights Vault · Hosted on Hugging Face · 78.5 MB
✓ Verified Direct URL
https://huggingface.co/soulfulari/soulfulariRVC/resolve/main/Usher2023_e550.zip
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.

★ Sweet Spot: MALE +12 st (4.66 MOS)
MALE reference · Pitch 0 st
NISQA Quality 2.42 / 5.0 · Sounds male
Semitone Shift (`-16` to `+16` st) · Bar height indicates NISQA clarity score
Female Ref
Male Ref
Audible Female Audible Male Amber border = Peak NISQA Quality
Raw model title: Usher (2023 Voice) (RVC V2) 550 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.

Age Profile
middle aged adult 59%
teenage 26%
elderly 12%
Music & Vocal Fit
speaking 47%
adlibs 19%
music 15%
Timbre & Texture
villain 48%
raspy 19%
energetic 17%
Best Use Case
gaming 68%
animation 13%
character 10%
Auditory Discovery · Close Alternatives

Voices That Sound Like Usher

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

Nearby voice
MALE · -4 st 4.42 MOS HF
Nearby voice
MALE · 0 st 4.75 MOS Drive
Michael Jackson Dangerous / HIStory Era
Nearby voice
MALE · -4 st 4.90 MOS HF
Nearby voice
MALE · -4 st 4.59 MOS HF
Heeseung from Enhypen
Nearby voice
MALE · -4 st 4.63 MOS HF
Michael Jackson Hugging Face
Nearby voice
MALE · -4 st 4.63 MOS HF
Model Documentation & Notes

About Usher (2023 Voice) (RVC V2) 550 Epochs

This model and dataset were made by me <@533897220030726146> . This dataset samples contains from his 3 recent singles of GLU, Good Good, and Boyfriend. Trained at RMVPE and 48Khz. **Please credit me <@533897220030726146> when using this model** `Inferencing settings: - Use RMVPE or RMVPE+` Link: https://huggingface.co/soulfulari/soulfulariRVC/resolve/main/Usher2023_e550.zip

Provenance & Open Access
Catalog ID:#1336
Weights Host:Hugging Face
Archive Size:78.5 MB
Rights & Safety: Report / Takedown