Stability AI Launches Music and Sound Generator  – 'Stable Audio'

Stability has recently launched their very first AI product that generates music and sound from descriptive text prompts along with a desired audio length. 

Stable Audio uses generative AI techniques to quickly produce high-quality music and sound effects in its user-friendly platform to ideally help musicians and creators. 

Now, these users can generate and download tracks of up to 20 seconds using the basic free version and up to 90 seconds with the Pro subscription – suitable for commercial projects.  

“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,” Emad Mostaque, CEO of Stability said. 

In a recent tweet, Stability officially launched their first generative product for music and sounds.

According to Stability, Stable Audio has powerful AI capabilities that enables users to:

• Create custom-length from descriptive text prompts powered by the latest audio diffusion models.
• Generate and download audio tracks in 44.1 kHz stereo,
• Use the generated audio in commercial projects.

In a release, it was stated that Stability curated the model in partnership with AudioSparx, an industry-leading music library that specializes in licensing high-quality audio contents for commercial use.  

Consequently, the model was trained using music and metadata from AudioSparx in efforts to “generate both economic and creative value” for all users.

Furthermore, this AI generator is intended for musicians who seek to create music samples that may potentially be included in their audio outputs, songs, or music.

Stability also pointed out that creators can use the generator with limitless opportunities. More so, the generated audio may be used for various types of content including songs, videos, podcasts and more.  

Definitely, it is interesting to see that Stability AI is finally venturing into other forms of generative AI models including a Japanese image-to-text generator, and now, a model dedicated to music and sounds. 

This AI model is totally a game-changer for creators and musicians because it has the ability to generate high-quality audio that can be used for commercial purposes too.