List your company

Zero-shot Text-to-Speech on TTS tasks Zero-shot

3.89UTMOSDiFlow-TTS-Small
2.31962.72733.1353.5427Sep 11, 2025

Evaluation results

MethodLinks
DiFlow-TTS-Small#Params=122M, NFE=16, RTF=0.052025.093.895458.580.008
DiFlow-TTS#Params=164M, NFE=16, RTF=0.072025.093.865457.960.007
MaskGCT#Params=1.43B, NFE=50 + 45†, RTF=0.462025.093.8396714.330.007
F5-TTS#Params=336M, NFE=32, RTF=0.262025.093.7296612.660.01
VALL-E#Params=594M, NFE=-, RTF=0.862025.093.68194021.660.02
VoiceCraft#Params=830M, NFE=-, RTF=1.702025.093.55185117.220.01
DiFlow-TTS-Small#Params=122M, NFE=4, RTF=0.032025.093.346438.310.007
DiFlow-TTS#Params=164M, NFE=4, RTF=0.032025.093.315448.050.007
OZSpeech#Params=145M, NFE=1, RTF=0.032025.093.1554011.960.01
NaturalSpeech 2#Params=378M, NFE=200, RTF=1.662025.092.3893115.620.02