List your company

Text-to-Audio on AudioCaps 2019 (test)

1.558FADUNISON (D24, 16kHz)
1.187123.690566.1948.69744May 29, 2026

Evaluation results

MethodLinks
UNISON (D24, 16kHz)Architecture=MM-DiT, Params=732M, Variant=D24, Sampling Rate=16kHz2026.051.55816.281.45910.950.3
GenAU-LArchitecture=DiT, Params=1.25B, substantially larger training data or preference optimization=true2026.051.59118.411.2911.9456.1
UNISON (D20, 44kHz)Architecture=MM-DiT, Params=621M, Variant=D20, Sampling Rate=44kHz2026.051.75615.821.45512.0446.7
TangoArchitecture=UNet, Params=866M2026.051.84624.521.3057.4549.8
Make-An-Audio 2Architecture=DiT, Params=937M2026.052.14220.141.59710.0244.1
Audio-OmniArchitecture=DiT, Params=3.05B2026.052.53531.421.3379.5548.6
AudioLDM 2-LargeArchitecture=UNet, Params=712M2026.053.09729.681.497.9845.2
UniSonateArchitecture=MM-DiT, Params=1.34B2026.054.2130.212.448.22—
MMAudio-LArchitecture=MM-DiT, Params=1.03B2026.055.89316.531.42111.9844.1
Stable Audio OpenArchitecture=DiT, Params=1.06B2026.0510.8352.033.0496.1320.3