AI startup Stability AI has partnered with chipmaker Arm to bring Stable Audio Open, an AI model capable of generating audio, to mobile devices with Arm chips. Unlike other AI-powered apps that rely on cloud processing, Stable Audio Open can be used offline. Additionally, the model’s training set consists entirely of royalty-free audio and songs, reducing the risk of copyright infringement.
Running on Arm chips, Stable Audio Open will be showcased at the Mobile World Congress conference in Barcelona, demonstrating its ability to generate audio based on text descriptions like “Gentle ocean waves at sunset.” Stability worked with Arm to optimize the model, significantly speeding up generation times. While the model is not yet available for download, Stability’s CEO hinted at plans to make it accessible to consumer apps and devices in the future.
Stability, known for its image generation model Stable Diffusion, has recently raised new funding and made strategic hires to revamp the business. With a new CEO in place and support from investors like Eric Schmidt and Sean Parker, the company is focused on optimizing Stable Audio Open for mobile devices in collaboration with Arm.
