32,011 Verified Open Models
28,877 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #33654 · Canonical Slug /model/1Kw01uf09gt
RVC v2
· 520 Epochs
Rocket Raccoon
Marvel's Guardians of the Galaxy, 520 epochs
RVC v2
520 Epochs
Peak Quality 4.60 MOS
Added Feb 5, 2026
★ 3 saved
https://huggingface.co/lyery/models-vc/resolve/main/rocket_m_520e_82680s.zip%3Fdownload%3Dtrue?download=true
Original uploaded URL returned HTTP 404 (huggingface.co/lyery/models-vc/rocket_m_520e_82680s.zip ) — automatically resolved to verified archive mirror above.
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 (4.60 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: Rocket Raccoon (Marvel's Guardians of the Galaxy, 520 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 Rocket Raccoon
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
Alex
Madagascar · English
Nearby voice
MALE · -4 st
4.89 MOS
HF
MALE · -12 st
4.86 MOS
HF
FEMALE · 0 st
4.64 MOS
HF
Model Documentation & Notes
About Rocket Raccoon (Marvel's Guardians of the Galaxy, 520 epochs)
download: https://huggingface.co/lyery/models-vc/resolve/main/rocket_m_520e_82680s.zip?download=true
he has almost 7 hours of voice lines but i only used 30 minutes, i could actually train a pretrain using all of the voice lines, but meh
-
steps: 82680
batch size: 4
sample rate: 32k
pretrain: original pretrain
Provenance & Open Access
Catalog ID: #33654
Weights Host: Hugging Face
