Fears are growing over the impact of generative AI on the music industry as London-based startup, Stability AI, releases Stable Audio 2.0. This latest version of the music-generation platform claims to set a new standard in AI-generated audio by creating high-quality, full tracks with coherent musical structures lasting up to three minutes in length.
Unlike its previous version, which only offered text-to-audio capabilities, Stable Audio 2.0 now includes an audio-to-audio feature. This feature allows users to upload copyright-free audio samples and transform them into a variety of sounds using natural language prompts.
Stability AI emphasizes that Stable Audio 2.0 was trained exclusively on a licensed dataset from the AudioSparx music library, comprising over 800,000 audio files. This ensures fair compensation for creators and respects opt-out requests.
The release of Stable Audio 2.0 comes at a time when concerns are being raised by artists like Billie Eilish and Nicki Minaj about the predatory use of AI in the music industry. Over 200 artists have signed an open letter calling for protection against the misuse of AI to replicate artists’ voices and likenesses.
The updated platform is now available for free on the Stable Audio website, allowing users to explore their musical creativity and create full-length compositions with ease.
Source link
