Stability AI releases a new family of audio models called Stability Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs (Ivan Mehta/TechCrunch)
Stability AI released Stability Audio 3.0, a new audio model family trained on licensed data, with the flagship model capable of generating six-minute songs—a significant jump over typical audio generation length limits.
Excerpt
<a href="https://techcrunch.com/2026/05/20/stability-ai-release-a-new-audio-model-that-can-create-six-minute-songs/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260520/i33.jpg" vspace="4" /></a>
<p><a href="https://www.techmeme.com/260520/p33#a260520p33" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Ivan Mehta / <a href="http://techcrunch.com/">TechCrunch</a>:<br />
<span style="font-size: 1.3em;"><b><a href="https://techcrunch.com/2026/05/20/stability-ai-release-a-new-audio-model-that-can-create-six-minute-songs/">Stability AI releases a new family of audio models called Stability Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs</a></b></span> — Stability AI, the company behind Stable Diffusion, is releasing a new family of audio models, called Stability Audio 3.0.</p>
Read at source: https://www.techmeme.com/260520/p33#a260520p33