Zero-shot Text-to-Speech on CV3-Eval Multi-lingual Voice Cloning English
4.73IMOSCosyEdit2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CosyEdit2Setting=Zero-shot2026.05 | 4.73 | 4.418 | |
| CosyVoice2Setting=Zero-shot2026.05 | 4.658 | 4.342 | |
| CosyEditSetting=Zero-shot2026.05 | 4.628 | 4.305 | |
| VoiceCraft-XSetting=Zero-shot2026.05 | 3.675 | 3.418 |