ModelMAEB · Audio ClusteringDimensionsMax inputLanguagesPriceReleased
eEbind Fullencord-teamOpen
26unstated
—0K tokensenNov 2025
22.7
768—enMay 2023
Msclap 2022MicrosoftOpen
19.9
———Dec 2022
Msclap 2023MicrosoftOpen
15.2
———Sep 2023
Qwen 2 Audio 7BAlibaba (Qwen)Open
12.7
—131K tokensenAug 2024
12.5
768——May 2023
7.7
768——May 2023
6.6
768——May 2023
6.2unstated
2,04833K tokensen, es, Estonian +80Apr 2026
6.1unstated
1,02433K tokens—$0.05 / 1M tokensApr 2026
lWav2cliplyrebirdOpen
6
———Mar 2022
6unstated
7688K tokens—$0.02 / 1M tokensApr 2026
5.3
768——May 2023
OMuQ MuLan LargeOpenMuQOpen
4.3
——en, zhJan 2025
3.7
—1K tokensenJul 2026
TOmniEmbed v0.1TevatronOpen
3.2unstated
—33K tokens—Apr 2025
LLanguageBind OmniLanguageBindOpen
2.9
—0K tokens—Oct 2023
2.7unstated
5128K tokens—$0.02 / 1M tokensOct 2026
HE5 Omni 3BHaon-ChenOpen
1.9unstated
2,04833K tokens—Jan 2026
HE5 Omni 7BHaon-ChenOpen
1.8unstated
3,58433K tokens—Jan 2026
LLCO Embedding Omni 7BLCO-EmbeddingOpen
1.7unstated
3,58433K tokens—Oct 2025
1.3
—66K tokensenSep 2025
LLCO Embedding Omni 3BLCO-EmbeddingOpen
1.3unstated
2,04833K tokens—Oct 2025
Speecht5 MultimodalMicrosoftOpen
1.1
768——May 2022
Qwen 2.5 Omni 7BAlibaba (Qwen)Open
0.7
—33K tokensenMar 2025
Qwen 2.5 Omni 3BAlibaba (Qwen)Open
0.6
—33K tokensenApr 2025