Text-to-Speech on ZTTS1-Eval In-The-Wild (ar)
10.51WERGemini 3.1 Flash
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gemini 3.1 Flashsupports zero-shot voice cloning=false2026.06 | 10.51 | 3.4 | 26.3 | |
| VoxCPM 22026.06 | 12.18 | 2.25 | 74.7 | |
| Eleven Labs V3supports zero-shot voice cloning=false2026.06 | 12.19 | 3.41 | 24.4 | |
| ZONOS2 8B Quality ModeQuality Mode=true2026.06 | 13.94 | 2.51 | 63.8 | |
| Inworld TTS 22026.06 | 14.85 | 2.7 | 60.5 | |
| Fish S2 Pro2026.06 | 15.59 | 2.58 | 72 | |
| Ground truth2026.06 | 21.05 | 2.22 | 81 | |
| ZONOS2 8BQuality Mode=false2026.06 | 21.43 | 2.22 | 67.4 |