25d ago in General discussion
Stability AI’s New Model Generates Audio from Text
Stability AI has launched Stable Audio Open, an open-source AI model that generates up to 47 seconds of audio from text descriptions. Trained on royalty-free samples, it allows users to create drum beats, instrument riffs, and ambient sounds, with the ability to fine-tune using custom audio data. While limited in producing full songs and vocals, this tool marks a significant step in AI-driven sound design. However, it cannot be used commercially and has some biases in musical styles. This release follows recent controversies and aims to promote Stability AI's commitment to responsible development.
0
0 comments
Stability AI’s New Model Generates Audio from Text
Public group
Improve your business with AI. For entrepreneurs, business owners, executives and creators.
powered by