Text-to-Speech on CV3-EN
2.43WERFish-Audio S2
Evaluation Results
| Method | Links | |
|---|---|---|
| Fish-Audio S22026.06 | 2.43 | |
| Raon-OpenTTS-1Bmode=zero-shot2026.05 | 3.92 | |
| dots.ttsTraining Stage=MF, NFE (Number of Function Evaluations)=42026.06 | 4.05 | |
| dots.ttsTraining Stage=SOAR2026.06 | 4.5 | |
| Qwen3-TTSmode=zero-shot2026.05 | 4.52 | |
| Raon-OpenTTS-0.3Bmode=zero-shot2026.05 | 4.62 | |
| CosyVoice 3mode=zero-shot2026.05 | 4.96 | |
| CosyVoice 3Number of Parameters=1.5B2026.06 | 4.99 | |
| VoxCPM 22026.06 | 5 | |
| VoxCPMmode=zero-shot2026.05 | 5.24 | |
| dots.ttsTraining Stage=Pretrain2026.06 | 5.24 | |
| CosyVoice 2mode=zero-shot2026.05 | 6.27 | |
| CosyVoice 22026.06 | 6.32 | |
| MaskGCTmode=zero-shot2026.05 | 7.73 | |
| F5-TTSmode=zero-shot2026.05 | 8.54 |