Stable Audio 2.0 is a significant upgrade to the original Stable Audio platform, introducing several new features and improvements1.
Stable Audio 2.0 sets a new standard in AI-generated audio by producing high-quality, full tracks with coherent musical structure up to three minutes in length at 44.1kHz stereo1. This is a substantial improvement over many existing models, providing users with longer, more complex compositions1.
Audio-to-Audio Generation
One of the most exciting features of Stable Audio 2.0 is its audio-to-audio generation capability1. Users can now upload audio samples and transform these samples into a wide array of sounds through natural language prompts1. This feature significantly expands the creative possibilities for users, allowing them to manipulate and enhance their audio in innovative ways1.
Expanded Sound Effect Generation and Style Transfer
Stable Audio 2.0 also expands sound effect generation and style transfer1. This provides artists and musicians with more flexibility and control, elevating their creative process1. Whether you’re looking to create unique sound effects or transfer the style of one piece of music to another, Stable Audio 2.0 has you covered1.
Fair Compensation for Creators
Stable Audio 2.0 was exclusively trained on a licensed dataset from the AudioSparx music library1. This ensures fair compensation for creators, honoring opt-out requests1.
Stable Audio 2.0 builds upon the success of Stable Audio 1.0, which debuted in September 20231. It has since been named one of TIME’s Best Inventions of 20231. With its new features and improvements, Stable Audio 2.0 continues to push the boundaries of AI-generated audio, offering an even more powerful tool for artists, musicians, and creators.
AI Advisory Boards 