Stability AI, a leading player in the world of generative AI, has now joined the ranks of tech giants like Google, Meta, and Open AI by introducing a groundbreaking model for generating music and sound clips. This innovative creation, named "Stable Audio," underwent training using a diverse array of sounds sourced from the extensive music library, Audio Sparx.
Distinguishing itself in the realm of music generation, Stability proudly claims Stable Audio as the pioneer in producing high-quality, 44.1 kHz music explicitly designed for commercial applications. This remarkable feat is achieved through a process known as "latent diffusion," a technique initially introduced for images via the company's flagship product, Stable Diffusion. Stable Audio, however, takes it a step further by utilizing text metadata, audio file duration, and start time to grant users unparalleled control over the generated audio content.
Users can effortlessly harness the power of Stable Audio by entering prompts like "post-rock, guitars, drum kit, bass, strings, euphoric, up-lifting, moody, flowing, raw, epic, sentimental, 125 BPM." The results are astounding, offering up to 20 seconds of sound on the free tier or a generous 90 seconds of audio for subscribers to the pro plan.
In their official announcement, Stability positions Music Generator Stable Audio as a versatile tool tailor-made for musicians looking to craft samples for their own compositions. Beyond that, this AI-generated music can seamlessly integrate into various commercial applications, including advertising campaigns and creator content.
Emad Mostaque, the CEO of Stability AI, expressed his excitement, stating, "As the only independent, open, and multimodal generative AI company, we are thrilled to use our expertise to develop a product in support of music creators. Our hope is that Stable Audio will empower music enthusiasts and creative professionals to generate new content with the help of AI, and we look forward to the endless innovations it will inspire."
Stability AI isn't a newcomer to the audio and music AI scene. The company already boasts an open-source generative audio label called HarmonAI, aimed at providing accessible and enjoyable music production tools "by musicians for musicians." Notably, key members of the HarmonAI team, including Ed Newton Rex, the VP of product, were actively involved in the development of Stable Audio, solidifying Stability's commitment to the world of music and AI.