List your company

Text-to-Speech on Seed-TTS-Eval (test)

1.33WERHoliTok
0.71924.84218.96513.0879May 20, 2026May 22, 2026May 24, 2026May 27, 2026May 29, 2026May 31, 2026Jun 3, 2026

Evaluation results

MethodLinks
HoliTokZero-shot=true2026.051.330.62
RobustSpeechFlowParams=0.06B, Zero-shot=true2026.051.380.6
ContrastiveFMParams=0.06B, Zero-shot=true2026.051.410.6
Semantic-VAEZero-shot=true2026.051.420.63
Baseline(SupertonicTTS)Params=0.06B, Zero-shot=true2026.051.440.6
Qwen3-TTSParameters=1.7B, Training Data=~ 5M, Open-Weight=true, Open-Data=false2026.051.460.715
MiniMax-SpeechZero-shot=true2026.051.650.69
DiTARParams=0.6B, Zero-shot=true2026.051.690.74
Seed-TTSDiTZero-shot=true2026.051.730.79
Raon-OpenTTS-1BParameters=1.0B, Training Data=510K, Open-Weight=true, Open-Data=true2026.051.780.749
MingTok-AudioZero-shot=true2026.051.840.61
VoxCPMParams=0.5B, Zero-shot=true2026.051.850.73
OpenAudio S1-MiniParams=0.5B, Zero-shot=true2026.051.940.55
Raon-OpenTTS-0.3BParameters=0.3B, Training Data=510K, Open-Weight=true, Open-Data=true2026.051.950.687
VoxCPMParameters=0.5B, Training Data=1.8M, Open-Weight=true, Open-Data=false2026.051.980.73
F5-TTSParams=0.3B, Zero-shot=true2026.0520.67
F5-TTSParameters=0.3B, Training Data=100K, Open-Weight=true, Open-Data=true2026.052.040.671
Human2026.052.140.734
Index-TTS 2Parameters=1.5B, Training Data=55K, Open-Weight=true, Open-Data=false2026.052.180.709
Voxtral TTSParameters=4B, Open-Weight=true, Open-Data=false2026.052.190.663
CosyVoice 3Parameters=1.5B, Training Data=~ 1M, Open-Weight=false, Open-Data=false2026.052.210.72
CosyVoice3Params=1.5B, Zero-shot=true2026.052.220.72
IndexTTS2Params=1.5B, Zero-shot=true2026.052.230.71
Seed-TTS2026.052.250.762
VoxCPM-EmiliaParams=0.5B, Zero-shot=true2026.052.340.68
CosyVoice 3Parameters=0.5B, Training Data=~ 1M, Open-Weight=true, Open-Data=false2026.052.50.698
MaskGCTParameters=0.6B, Training Data=100K, Open-Weight=true, Open-Data=true2026.052.570.713
CosyVoice 2Parameters=0.5B, Training Data=170K, Open-Weight=true, Open-Data=false2026.052.610.659
MegaTTS3Params=0.5B, Zero-shot=true2026.052.790.77
VibeVoiceParams=1.5B, Zero-shot=true2026.053.040.69
Spark-TTSParams=0.5B, Zero-shot=true2026.053.140.57
LlasaParameters=8B, Training Data=250K, Open-Weight=true, Open-Data=false2026.053.630.581
CleanCodecToken Rate (t/s)=12.5, Train Time (hh:mm)=01:00, RTF (RTFx)=0.170 (5.9x)2026.063.90.56
XCodec2Token Rate (t/s)=50, Train Time (hh:mm)=02:44, RTF (RTFx)=0.688 (1.5x)2026.064.90.4
BiCodecToken Rate (t/s)=50, Train Time (hh:mm)=02:49, RTF (RTFx)=0.691 (1.4x)2026.065.20.51
KanadeToken Rate (t/s)=12.5, Train Time (hh:mm)=00:59, RTF (RTFx)=0.169 (5.9x)2026.065.60.45
Qwen3Token Rate (t/s)=200, Train Time (hh:mm)=10:02, RTF (RTFx)=2.930 (0.3x)2026.069.10.36
MimiToken Rate (t/s)=100, Train Time (hh:mm)=05:11, RTF (RTFx)=1.452 (0.7x)2026.0610.80.34
FocalCodecToken Rate (t/s)=12.5, Train Time (hh:mm)=00:58, RTF (RTFx)=0.172 (5.8x)2026.0612.20.31
WavTokenizerToken Rate (t/s)=40, Train Time (hh:mm)=02:19, RTF (RTFx)=0.552 (1.8x)2026.0616.60.37