32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #25441 · Canonical Slug /model/1rqG5JxjwIg
RVC v2
· Crepe
· 300 Epochs
Elsa | 40K | Mangio Crepe
Frozen
RVC v2
Crepe
300 Epochs
Peak Quality 4.93 MOS
Added Feb 23, 2024
★ 4 saved
https://huggingface.co/SCRFilms/ElsaFrozenV4/resolve/main/Elsa_V5_40K.zip?download=true
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 (4.93 MOS)
Female Ref
-16
4.5
-12
4.7
-8
4.5
-4
4.5
0
4.6
+4
4.7
+8
4.3
+12
4.1
+16
3.9
Male Ref
-16
4.0
-12
4.6
-8
4.8
-4
4.8
0
4.8
+4
4.9
+8
4.9
+12
4.9
+16
4.7
Audible Female
Audible Male
Amber border = Peak NISQA Quality
Raw model title: Elsa (Frozen) | RVC 2 40K | Mangio Crepe 300 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 Elsa | 40K | Mangio Crepe
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
FEMALE · +4 st
4.59 MOS
HF
FEMALE · 0 st
3.62 MOS
HF
MALE · +12 st
4.60 MOS
HF
FEMALE · +4 st
4.25 MOS
HF
Gregory
Five Nights at Freddy's, FNAF, Security Breach, RMVPE
Nearby voice
MALE · +16 st
4.45 MOS
HF
Model Documentation & Notes
About Elsa (Frozen) | RVC 2 40K | Mangio Crepe 300 Epochs
Updated model as of 2/24/24. Highest quality and accurate voice model of Elsa, big improvement from the past 6 months. The dataset are now merged with talking and singing. Don't forget to credit me when model is used hehe.
Tip: De-Reverb your audio first before inferencing.
Dataset Info:
- Songs and Dialogue from Frozen 2 and Olaf's Frozen Adventure
- 40Khz Sample Rate
- 6 Minutes and 30 Seconds Length
Training Settings:
- Mangio Crepe
- 8 Hop Length
- 4 Batch Size
- 200 Epochs
- 40K Sample Rate
- Normal V2 Pretrain
Model Link:
https://huggingface.co/SCRFilms/ElsaFrozenV4/resolve/main/Elsa_V5_40K.zip?download=true
Provenance & Open Access
Catalog ID: #25441
Weights Host: Hugging Face
Archive Size: 87.3 MB