Zero-shot Voice Cloning on Seed-TTS-Eval en (test)
1.23WER (%)Qwen3-TTS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-TTSParams=1.7B2026.06 | 1.23 | 71.7 | |
| dots.tts (MF, NFE=4)Params=2B, Distillation Method=MeanFlow, NFE=42026.06 | 1.29 | 76.2 | |
| dots.tts (SOAR)Params=2B, Variant=SOAR2026.06 | 1.3 | 77.1 | |
| dots.tts (Pretrain)Params=2B, Variant=Pretrain2026.06 | 1.34 | 76.8 | |
| dots.tts (MF, NFE=3)Params=2B, Distillation Method=MeanFlow, NFE=32026.06 | 1.41 | 75.9 | |
| dots.tts (MF, NFE=2)Params=2B, Distillation Method=MeanFlow, NFE=22026.06 | 1.51 | 75.2 | |
| MiniMax-Speech2026.06 | 1.65 | 69.2 | |
| DiTARParams=0.6B2026.06 | 1.69 | 73.5 | |
| VoxCPM 2Params=2B2026.06 | 1.84 | 75.3 | |
| FireRedTTS 2Params=1.5B2026.06 | 1.95 | 66.5 | |
| F5-TTSParams=0.3B2026.06 | 2 | 67 | |
| CosyVoice 3Params=1.5B2026.06 | 2.22 | 72 | |
| IndexTTS 2Params=1.5B2026.06 | 2.23 | 70.6 | |
| Seed-TTS2026.06 | 2.25 | 76.2 | |
| MegaTTS 3Params=0.5B2026.06 | 2.79 | 77.1 | |
| VibeVoiceParams=1.5B2026.06 | 3.04 | 68.9 |