Text-to-Speech on English TTS Evaluation (EN) (test)
0.734SIM-oGround Truth
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ground TruthFramework=–2026.01 | 0.734 | 2.14 | |
| MaskGCTFramework=TTS2026.01 | 0.713 | 2.26 | |
| E2-TTSFramework=TTS2026.01 | 0.706 | 2.49 | |
| ZipVoiceFramework=TTS2026.01 | 0.697 | 1.7 | |
| F5-TTSFramework=TTS2026.01 | 0.664 | 1.89 | |
| CosyVoice2Framework=TTS2026.01 | 0.652 | 2.57 | |
| M3-TTSFramework=TTS2026.01 | 0.604 | 1.36 | |
| MM-SonateFramework=Unified2026.01 | 0.604 | 2.065 |