Directory

Audio models

AI audio, music and speech models compared by creator, pricing, release date and provider availability.

13 models · Showing 1–13

Select models to compareModelReleasedContextInput /MOutput /MParametersTypeI/OOpenness
Qwen-Omni TurboAlibabaJanuary 19, 202533K———Text, Audiotext, image, audio, video → text, audioClosed
Gemini 2.5 Flash TTSGoogle DeepMindSeptember 30, 202533K———Audiotext → audioClosed
Gemini 2.5 Pro TTSGoogle DeepMindSeptember 30, 202533K———Audiotext → audioClosed
GPT Audio MiniOpenAIOctober 6, 2025128K$0.60$2.40—Text, Audiotext, audio → text, audioClosed
GPT AudioOpenAIJanuary 19, 2026128K$2.50$10.00—Text, Audiotext, audio → text, audioClosed
Seedance 2.0ByteDance SeedFebruary 12, 2026————Video, Audiotext, image, video, audio → video, audioClosed
Lyria 3 Clip PreviewGoogle DeepMindMarch 25, 20261.0M$0.00$0.00—Text, Audiotext, image → text, audioClosed
Lyria 3 Pro PreviewGoogle DeepMindMarch 25, 20261.0M$0.00$0.00—Text, Audiotext, image → text, audioClosed
Gemini 3.1 Flash Live PreviewGoogle DeepMindMarch 26, 2026131K———Text, Audiotext, image, video, audio → text, audioClosed
Gemini 3.5 Live Translate PreviewGoogle DeepMindJune 9, 2026131K———Audio, Textaudio → audio, textClosed
GPT-Realtime-2.1OpenAIJuly 6, 2026128K———Text, Audiotext, audio, image → text, audioClosed
MiniMax H3MiniMaxJuly 31, 2026————Video, Audiotext, image, video, audio → video, audioOpen weights
Seedance 2.5ByteDance SeedJuly 31, 2026————Video, Audiotext, image, video, audio → video, audioClosed
Page 1 of 1