Multilingual Speech Generation on TTS multilingual (test)
0.447WERQwen3.5-Omni-Plus
Evaluation results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-Omni-PlusLanguage=German2026.04 | 0.447 | — | — | — | — | — | — | — | — | — | — | 75.7 | |
| Qwen3.5-Omni-PlusLanguage=Italian2026.04 | 0.503 | — | — | — | — | — | — | — | — | — | — | 78.5 | |
| ElevenLabsLanguage=German2026.04 | 0.572 | — | — | — | — | — | — | — | — | — | — | 61.4 | |
| Qwen3.5-Omni-PlusLanguage=English2026.04 | 0.631 | — | — | — | — | — | — | — | — | — | — | 83.3 | |
| Qwen3.5-Omni-PlusLanguage=Chinese2026.04 | 0.695 | — | — | — | — | — | — | — | — | — | — | 80 | |
| ElevenLabsLanguage=Turkish2026.04 | 0.699 | — | — | — | — | — | — | — | — | — | — | 59.6 | |
| ElevenLabsLanguage=English2026.04 | 0.756 | — | — | — | — | — | — | — | — | — | — | 61.3 | |
| ElevenLabsLanguage=Polish2026.04 | 0.766 | — | — | — | — | — | — | — | — | — | — | 72.9 | |
| ElevenLabsLanguage=Dutch2026.04 | 0.803 | — | — | — | — | — | — | — | — | — | — | 68 | |
| Qwen3.5-Omni-PlusLanguage=Indonesian2026.04 | 0.823 | — | — | — | — | — | — | — | — | — | — | 78 | |
| Qwen3.5-Omni-PlusLanguage=Spanish2026.04 | 0.862 | — | — | — | — | — | — | — | — | — | — | 79.7 | |
| MiniMaxLanguage=Vietnamese2026.04 | 0.88 | — | — | — | — | — | — | — | — | — | — | 74.3 | |
| Qwen3.5-Omni-PlusLanguage=Turkish2026.04 | 0.938 | — | — | — | — | — | — | — | — | — | — | 74.7 | |
| MiniMaxLanguage=Spanish2026.04 | 1.029 | — | — | — | — | — | — | — | — | — | — | 76.2 | |
| ElevenLabsLanguage=Indonesian2026.04 | 1.059 | — | — | — | — | — | — | — | — | — | — | 66 | |
| ElevenLabsLanguage=Spanish2026.04 | 1.084 | — | — | — | — | — | — | — | — | — | — | 61.5 | |
| Qwen3.5-Omni-PlusLanguage=Vietnamese2026.04 | 1.143 | — | — | — | — | — | — | — | — | — | — | 76.7 | |
| MiniMaxLanguage=Dutch2026.04 | 1.143 | — | — | — | — | — | — | — | — | — | — | 73.8 | |
| Qwen3.5-Omni-PlusLanguage=Portuguese2026.04 | 1.221 | — | — | — | — | — | — | — | — | — | — | 79.2 | |
| MiniMaxLanguage=Indonesian2026.04 | 1.237 | — | — | — | — | — | — | — | — | — | — | 72.9 | |
| Qwen3.5-Omni-PlusLanguage=Dutch2026.04 | 1.238 | — | — | — | — | — | — | — | — | — | — | 76.2 | |
| ElevenLabsLanguage=Portuguese2026.04 | 1.331 | — | — | — | — | — | — | — | — | — | — | 71.1 | |
| MiniMaxLanguage=Polish2026.04 | 1.415 | — | — | — | — | — | — | — | — | — | — | 80.2 | |
| Qwen3.5-Omni-PlusLanguage=Polish2026.04 | 1.427 | — | — | — | — | — | — | — | — | — | — | 83.9 | |
| Qwen3.5-Omni-PlusLanguage=Korean2026.04 | 1.458 | — | — | — | — | — | — | — | — | — | — | 74.7 | |
| MiniMaxLanguage=Turkish2026.04 | 1.52 | — | — | — | — | — | — | — | — | — | — | 77.9 | |
| MiniMaxLanguage=Italian2026.04 | 1.543 | — | — | — | — | — | — | — | — | — | — | 69.9 | |
| MiniMaxLanguage=Arabic2026.04 | 1.665 | — | — | — | — | — | — | — | — | — | — | 73.6 | |
| ElevenLabsLanguage=Arabic2026.04 | 1.666 | — | — | — | — | — | — | — | — | — | — | 70.6 | |
| ElevenLabsLanguage=Italian2026.04 | 1.743 | — | — | — | — | — | — | — | — | — | — | 67.9 | |
| MiniMaxLanguage=Korean2026.04 | 1.747 | — | — | — | — | — | — | — | — | — | — | 77.6 | |
| ElevenLabsLanguage=Korean2026.04 | 1.865 | — | — | — | — | — | — | — | — | — | — | 70 | |
| MiniMaxLanguage=Portuguese2026.04 | 1.877 | — | — | — | — | — | — | — | — | — | — | 80.5 | |
| MiniMaxLanguage=German2026.04 | 1.906 | — | — | — | — | — | — | — | — | — | — | 73.3 | |
| ElevenLabsLanguage=Czech2026.04 | 2.108 | — | — | — | — | — | — | — | — | — | — | 68.5 | |
| MiniMaxLanguage=English2026.04 | 2.164 | — | — | — | — | — | — | — | — | — | — | 75.6 | |
| Qwen3.5-Omni-PlusLanguage=Thai2026.04 | 2.17 | — | — | — | — | — | — | — | — | — | — | 78.8 | |
| MiniMaxLanguage=Chinese2026.04 | 2.252 | — | — | — | — | — | — | — | — | — | — | 78 | |
| Qwen3.5-Omni-PlusLanguage=French2026.04 | 2.43 | — | — | — | — | — | — | — | — | — | — | 73 | |
| Qwen3.5-Omni-PlusLanguage=Arabic2026.04 | 2.602 | — | — | — | — | — | — | — | — | — | — | 74.5 | |
| MiniMaxLanguage=Thai2026.04 | 2.701 | — | — | — | — | — | — | — | — | — | — | 80 | |
| Qwen3.5-Omni-PlusLanguage=Finnish2026.04 | 2.784 | — | — | — | — | — | — | — | — | — | — | 85.9 | |
| Qwen3.5-Omni-PlusLanguage=Czech2026.04 | 2.929 | — | — | — | — | — | — | — | — | — | — | 80.2 | |
| ElevenLabsLanguage=Finnish2026.04 | 2.964 | — | — | — | — | — | — | — | — | — | — | 75.9 | |
| Qwen3.5-Omni-PlusLanguage=Russian2026.04 | 3.182 | — | — | — | — | — | — | — | — | — | — | 79 | |
| Qwen3.5-Omni-PlusLanguage=Japanese2026.04 | 3.479 | — | — | — | — | — | — | — | — | — | — | 78.8 | |
| MiniMaxLanguage=Japanese2026.04 | 3.519 | — | — | — | — | — | — | — | — | — | — | 77.6 | |
| MiniMaxLanguage=Czech2026.04 | 3.875 | — | — | — | — | — | — | — | — | — | — | 79.6 | |
| ElevenLabsLanguage=Russian2026.04 | 3.878 | — | — | — | — | — | — | — | — | — | — | 67.6 | |
| MiniMaxLanguage=French2026.04 | 4.099 | — | — | — | — | — | — | — | — | — | — | 62.8 | |
| MiniMaxLanguage=Russian2026.04 | 4.281 | — | — | — | — | — | — | — | — | — | — | 76.1 | |
| MiniMaxLanguage=Finnish2026.04 | 4.666 | — | — | — | — | — | — | — | — | — | — | 83.5 | |
| ElevenLabsLanguage=French2026.04 | 5.216 | — | — | — | — | — | — | — | — | — | — | 53.5 | |
| ElevenLabsLanguage=Hindi2026.04 | 5.827 | — | — | — | — | — | — | — | — | — | — | 73 | |
| Qwen3.5-Omni-PlusLanguage=Hindi2026.04 | 6.444 | — | — | — | — | — | — | — | — | — | — | 79.7 | |
| MiniMaxLanguage=Hindi2026.04 | 6.962 | — | — | — | — | — | — | — | — | — | — | 81.8 | |
| ElevenLabsLanguage=Japanese2026.04 | 10.046 | — | — | — | — | — | — | — | — | — | — | 73.8 | |
| ElevenLabsLanguage=Chinese2026.04 | 16.026 | — | — | — | — | — | — | — | — | — | — | 67.7 | |
| ElevenLabsLanguage=Vietnamese2026.04 | 73.415 | — | — | — | — | — | — | — | — | — | — | 36.9 | |
| ElevenLabsLanguage=Thai2026.04 | 73.936 | — | — | — | — | — | — | — | — | — | — | 58.8 | |
| ElevenLabs2026.01 | — | 16.026 | 2.339 | 0.572 | 1.743 | 1.331 | 1.084 | 10.646 | 1.865 | 5.216 | 3.878 | — | |
| ElevenLabs2026.01 | — | 0.677 | 0.613 | 0.614 | 0.579 | 0.711 | 0.615 | 0.738 | 0.7 | 0.535 | 0.676 | — | |
| MiniMax2026.01 | — | 2.252 | 2.164 | 1.906 | 1.543 | 1.877 | 1.029 | 3.519 | 1.747 | 4.099 | 4.281 | — | |
| MiniMax2026.01 | — | 0.78 | 0.756 | 0.733 | 0.699 | 0.805 | 0.762 | 0.776 | 0.776 | 0.628 | 0.761 | — | |
| Qwen3-TTSSampling Rate=25Hz, Model Scale=0.6B-Base2026.01 | — | 1.108 | 1.048 | 1.501 | 1.169 | 2.046 | 2.031 | 4.189 | 2.458 | 2.852 | 5.957 | — | |
| Qwen3-TTSSampling Rate=25Hz, Model Scale=1.7B-Base2026.01 | — | 0.777 | 1.014 | 0.96 | 1.105 | 1.778 | 1.491 | 5.121 | 2.695 | 2.631 | 4.535 | — | |
| Qwen3-TTSSampling Rate=12Hz, Model Scale=0.6B-Base2026.01 | — | 1.145 | 0.836 | 1.089 | 1.534 | 2.254 | 1.491 | 6.404 | 1.741 | 2.931 | 4.458 | — | |
| Qwen3-TTSSampling Rate=12Hz, Model Scale=1.7B-Base2026.01 | — | 0.928 | 0.934 | 1.235 | 0.948 | 1.526 | 1.126 | 3.823 | 1.755 | 2.858 | 3.212 | — | |
| Qwen3-TTSSampling Rate=25Hz, Model Scale=0.6B-Base2026.01 | — | 0.797 | 0.811 | 0.749 | 0.722 | 0.79 | 0.732 | 0.81 | 0.824 | 0.698 | 0.734 | — | |
| Qwen3-TTSSampling Rate=25Hz, Model Scale=1.7B-Base2026.01 | — | 0.796 | 0.815 | 0.737 | 0.718 | 0.783 | 0.731 | 0.807 | 0.814 | 0.703 | 0.744 | — | |
| Qwen3-TTSSampling Rate=12Hz, Model Scale=0.6B-Base2026.01 | — | 0.811 | 0.829 | 0.769 | 0.792 | 0.794 | 0.812 | 0.798 | 0.812 | 0.7 | 0.781 | — | |
| Qwen3-TTSSampling Rate=12Hz, Model Scale=1.7B-Base2026.01 | — | 0.799 | 0.775 | 0.775 | 0.817 | 0.817 | 0.814 | 0.788 | 0.799 | 0.714 | 0.792 | — |