Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-speaker Dialogue Synthesis on CoVoMix2 Dialogue-WildRef (test)
Loading...
0.156
cpWER
MOSS-TTSD
0.15136
0.18268
0.214
0.24532
Jun 17, 2026
cpWER
cpSIM
Accuracy
WER
SIM-O
UTMOS
SQUIM
Updated 1mo ago
Evaluation Results
Method
Method
Links
cpWER
cpSIM
Accuracy
WER
SIM-O
UTMOS
SQUIM
MOSS-TTSD
2026.06
0.156
0.39
84.4
0.059
0.295
3.45
4.21
SCENA
2026.06
0.167
0.424
81.9
0.022
0.348
3.3
4.28
VibeVoice
model_size=7B
2026.06
0.172
0.386
84.1
0.045
0.317
2.56
2.91
ZipVoice-Dialog
2026.06
0.173
0.396
82.5
0.038
0.315
3.2
4.19
VibeVoice
model_size=1.5B
2026.06
0.202
0.365
82.6
0.089
0.293
2.33
2.85
Dia
source=Nari Labs
2026.06
0.272
0.278
75.2
0.086
0.256
2.45
3.92
Feedback
Search any
task
Search any
task