Stability AI launches Stable Audio 3.0 with up to six-minute tracks and open weights

Stability AI has launched Stable Audio 3.0, introducing a new generation of audio models, three of which come with open weights. These models can generate music tracks lasting up to six minutes and were trained entirely on licensed data. This launch marks a significant advancement in audio model development, enabling users to access advanced musical tools without restrictions. The use of licensed data enhances the models' credibility and ensures high-quality outputs.