Zero-shot Voice Cloning on Seed-TTS-Eval zh (test)
0.83WERMiniMax-Speech
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MiniMax-Speech2026.06 | 0.83 | 78.3 | |
| dots.tts (SOAR)Params=2B, Variant=SOAR2026.06 | 0.94 | 81 | |
| dots.tts (MF, NFE=4)Params=2B, Distillation Method=MeanFlow, NFE=42026.06 | 0.94 | 80 | |
| dots.tts (Pretrain)Params=2B, Variant=Pretrain2026.06 | 0.96 | 80.5 | |
| VoxCPM 2Params=2B2026.06 | 0.97 | 79.5 | |
| DiTARParams=0.6B2026.06 | 1.02 | 75.3 | |
| dots.tts (MF, NFE=3)Params=2B, Distillation Method=MeanFlow, NFE=32026.06 | 1.02 | 79.9 | |
| IndexTTS 2Params=1.5B2026.06 | 1.03 | 76.5 | |
| dots.tts (MF, NFE=2)Params=2B, Distillation Method=MeanFlow, NFE=22026.06 | 1.04 | 79.1 | |
| CosyVoice 3Params=1.5B2026.06 | 1.12 | 78.1 | |
| Seed-TTS2026.06 | 1.12 | 79.6 | |
| FireRedTTS 2Params=1.5B2026.06 | 1.14 | 73.6 | |
| VibeVoiceParams=1.5B2026.06 | 1.16 | 74.4 | |
| Qwen3-TTSParams=1.7B2026.06 | 1.22 | 77 | |
| MegaTTS 3Params=0.5B2026.06 | 1.52 | 79 | |
| F5-TTSParams=0.3B2026.06 | 1.53 | 76 |