Text-to-Speech on Chinese TTS Evaluation ZH (test)
77.3SIM-oMaskGCT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MaskGCTFramework=TTS2026.01 | 77.3 | 2.4 | |
| Ground TruthFramework=–2026.01 | 75.5 | 1.25 | |
| ZipVoiceFramework=TTS2026.01 | 75.1 | 1.4 | |
| F5-TTSFramework=TTS2026.01 | 75 | 1.53 | |
| CosyVoice2Framework=TTS2026.01 | 74.8 | 1.45 | |
| E2-TTSFramework=TTS2026.01 | 71.3 | 1.91 | |
| MM-SonateFramework=Unified2026.01 | 69.1 | 2.768 | |
| M3-TTSFramework=TTS2026.01 | 62.1 | 1.31 |