Stability AI recently issued a press release announcing the launch of Stable Audio 2.0, which can generate a complete audio track of up to 3 minutes based on the prompt words entered by the user.
Stable Audio 2.0 further expands the audio generation with intro, chorus, outro, and stereo effects based on the previous version 1.0.The maximum length of audio content that can be generated is 3 minutes.
In addition to expanding the generation function, Stable Audio 2.0 also provides an audio generation function, which can expand the generation and supplement related audio content based on a short audio content uploaded by the user. IT Home attaches a demonstration video as follows:
For example, if a musician is "stuck" when composing a piece of music, he can upload a DEMO and ask Stable Audio 2.0 to complete the song, so that all your small creative ideas can be converted into complete audio content.
Stable Audio 2.0 also supports customization and fine-tuning of the generated audio content. In other words, if you don’t like something in the audio, you can change the style according to your specific needs.
Stability Audio 2.0 not only generates complete soundtracks, it also helps you create a wide range of sounds and audio effects, from typing sounds to crowd background noises and more.