Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Text-to-Audio Generation research benchmarks – Page 2 · SOTA2 Research

Text-to-Audio Generation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

AudioCaps 5s (test)

Make-An-Audio 2

13.78FD (Fréchet Distance)

3

Feb 26, 2026

Clotho eval 10s (test)

Make-An-Audio 2

19.97FD

3

Feb 26, 2026

0.57Stereo Correctness

1

Feb 26, 2026

Page 2 of 2

Popular datasets

AudioCaps Clotho MusicCaps VGGSound AudioSet

Follow for updates

Join SOTA2 Contact