Text-to-Speech (Text and Reference Speech input) on Emotion TTS (EN) Hard
93.4ACC-IGroud-truth
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Groud-truth2026.01 | 93.4 | 0.6 | 1 | — | |
| FlexiVoice2026.01 | 78.2 | 10.6 | 0.87 | 95.8 | |
| CosyVoice22026.01 | 61 | 14.4 | 0.84 | 99.8 | |
| VoxInstruct2026.01 | 49.7 | 23.9 | 0.8 | 90.6 | |
| FlexiVoice-Base2026.01 | 48.8 | 32.2 | 0.78 | 99.4 |