Stability AI introduced Stable Audio 2.0, an upgraded version of its music creation platform. This system allows users to create up to three minutes of audio via text prompt. It should be noted that the previous version of the software reached a maximum of 90 seconds. Since this is about the length of a song, it can also start an intro, a full chord progression, and an outro. Additionally, the tool is free and available to the public via the company’s website.
Stable Audio 2.0 works via text prompt, but there is also an option to load audio clips. The system analyzes the clip and can produce something similar. It is also underlined that all uploaded sounds must be copyright-free.
On the other hand, it should not be forgotten that this is still music produced by artificial intelligence. For example, the system likes to add vocals, but this is not possible in any known human language. We think that the language used in the text in the images created by artificial intelligence is used.
However, let’s not forget to say that the sound generator continues to develop and it is certain that it will produce better things.
Follow our site to read more technology news!
