32,022 Verified Open Models
28,886 Multi-Pitch Audition Ready
100% Direct Source URLs (HF · Drive · MEGA)
Model ID #751 · Canonical Slug /model/1mP3oITtzsA
RVC v2
· 180 Epochs
Astarion
Baldur's Gate 3 · 30m, 50ms padding
RVC v2
180 Epochs
Added Sep 4, 2023
https://huggingface.co/datasets/quietwhisper/rvc-bd3-astarion/blob/main/180e-30m-50ms.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.
18 Reference Previews
Female Ref
-16
-12
-8
-4
0
+4
+8
+12
+16
Male Ref
-16
-12
-8
-4
0
+4
+8
+12
+16
Raw model title: Astarion (Baldur's Gate 3) (RVC V2) (180 epochs) (30m, 50ms padding)
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: 180 Epochs · Source Host: Hugging Face
Auditory Discovery · Close Alternatives
Voices That Sound Like Astarion
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
High-clarity female voice
FEMALE · 0 st
5.10 MOS
HF
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 Astarion (Baldur's Gate 3) (RVC V2) (180 epochs) (30m, 50ms padding)
https://huggingface.co/datasets/quietwhisper/rvc-bd3-astarion/blob/main/180e-30m-50ms.zip
Trained from game assets' samples directly over mono channel. 50ms padding between samples. Only trained 180 epochs as after the regression becomes positive and the model is overtraining. I also tried larger samples but it seems that it's not immediatelly clear that more data is better in fidelity so far. If someone requires to fine tune this further let me know
Provenance & Open Access
Catalog ID: #751
Weights Host: Hugging Face
Archive Size: 173.9 MB
