Voice Cloning on SEED-TTS-Eval ZH (test)
0.54CERFish Audio S2
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Fish Audio S2Parameters=4B, Open-source=true, Zero-shot=true2026.06 | 0.54 | — | — | |
| MiniMax-SpeechOpen-source=false, Zero-shot=true2026.06 | 0.83 | — | 78.3 | |
| OmniVoiceParameters=0.8B, Open-source=true, Zero-shot=true2026.06 | 0.84 | — | 77.7 | |
| CosyVoice3.5Open-source=false, Zero-shot=true2026.06 | 0.87 | — | 79.7 | |
| VoxCPMParameters=0.6B, Open-source=true, Zero-shot=true2026.06 | 0.93 | — | 77.2 | |
| VoxCPM2Parameters=2B, Open-source=true, Zero-shot=true2026.06 | 0.97 | — | 79.5 | |
| DiTARParameters=0.6B, Open-source=false, Zero-shot=true2026.06 | 1.02 | — | 75.3 | |
| Index-TTS 2Params=1.5B, Category=Multi-Stage or NAR Methods, Independent control of timbre and prosody=true2025.12 | 1.03 | 0.765 | — | |
| IndexTTS2Parameters=1.5B, Open-source=true, Zero-shot=true2026.06 | 1.03 | — | 76.5 | |
| Qwen3-OmniParameters=30B-A3B, Open-source=true, Zero-shot=true2026.06 | 1.07 | — | — | |
| LongCat-Audio-DiTParameters=3.5B, Open-source=true, Zero-shot=true2026.06 | 1.09 | — | 81.8 | |
| CosyVoice 3Parameters=1.5B, Open-source=false, Zero-shot=true2026.06 | 1.12 | — | 78.1 | |
| Seed-TTSOpen-source=false, Zero-shot=true2026.06 | 1.12 | — | 79.6 | |
| FireRedTTS-2Parameters=1.5B, Open-source=true, Zero-shot=true2026.06 | 1.14 | — | 73.6 | |
| CosyVoice 3Parameters=0.5B, Open-source=true, Zero-shot=true2026.06 | 1.16 | — | 78 | |
| VibeVoiceParameters=1.5B, Open-source=true, Zero-shot=true2026.06 | 1.16 | — | 74.4 | |
| OpenAudio-s1-miniParameters=0.5B, Open-source=true, Zero-shot=true2026.06 | 1.18 | — | 68.5 | |
| VoxCPM1.5Parameters=0.8B, Open-source=true, Zero-shot=true2026.06 | 1.18 | — | 77 | |
| Spark-TTSParams=0.5B, Category=One-Stage AR Methods, Independent control of timbre and prosody=false2025.12 | 1.2 | 0.672 | — | |
| MOSS-TTSParameters=8B, Open-source=true, Zero-shot=true2026.06 | 1.2 | — | 78.8 | |
| Qwen3-TTSParameters=1.7B, Open-source=true, Zero-shot=true2026.06 | 1.22 | — | 77 | |
| CosyVoice 2Parameters=0.5B, Open-source=true, Zero-shot=true2026.06 | 1.38 | — | 75.7 | |
| ZipVoiceParameters=0.1B, Open-source=true, Zero-shot=true2026.06 | 1.4 | — | 75.1 | |
| CosyVoice2Params=0.5B, Category=Multi-Stage or NAR Methods, Independent control of timbre and prosody=false2025.12 | 1.45 | 0.748 | — | |
| HiggsAudio-v2Parameters=3B, Open-source=true, Zero-shot=true2026.06 | 1.5 | — | 74 | |
| FireRedTTSParams=N/A, Category=Multi-Stage or NAR Methods, Independent control of timbre and prosody=false2025.12 | 1.51 | 0.635 | — | |
| FireRedTTSParameters=0.5B, Open-source=true, Zero-shot=true2026.06 | 1.51 | — | 63.5 | |
| MegaTTS3Parameters=0.5B, Open-source=false, Zero-shot=true2026.06 | 1.52 | — | 79 | |
| F5-TTSParameters=0.3B, Open-source=true, Zero-shot=true2026.06 | 1.53 | — | 76 | |
| Spark-TTSParameters=0.5B, Open-source=true, Zero-shot=true2026.06 | 1.54 | — | 66 | |
| F5-TTSParams=0.3B, Category=Multi-Stage or NAR Methods, Independent control of timbre and prosody=false2025.12 | 1.56 | 0.741 | — | |
| Qwen2.5-OmniParameters=7B, Open-source=true, Zero-shot=true2026.06 | 1.7 | — | 75.2 | |
| Llasa-1BParams=1B, Category=One-Stage AR Methods, Independent control of timbre and prosody=false2025.12 | 1.89 | 0.669 | — | |
| DisCo-SpeechParams=1.5B, Category=One-Stage AR Methods, Independent control of timbre and prosody=true2025.12 | 2.08 | 0.677 | — | |
| MaskGCTParameters=1B, Open-source=true, Zero-shot=true2026.06 | 2.27 | — | 77.4 | |
| CosyVoiceParameters=0.3B, Open-source=true, Zero-shot=true2026.06 | 3.63 | — | 72.3 | |
| VevoParams=N/A, Category=Multi-Stage or NAR Methods, Independent control of timbre and prosody=true2025.12 | 3.99 | 0.723 | — |