AI Startup Teams Up with Chipmaker Arm to Bring AI-Powered Audio Generation to Mobile Devices

AI-Powered Audio Generation

AI startup Stability has teamed up with chipmaker Arm to bring its AI model, Stable Audio Open, to mobile devices running Arm chips. This move enables the generation of audio, including sound effects, on mobile devices.

Limitations of Current AI-Powered Audio Generation

While several AI-powered apps can generate audio, most rely on cloud processing, making them unavailable offline. Additionally, some audio generation models were trained on copyrighted content, posing an intellectual property risk. Stability claims that its Stable Audio Open’s training set is composed entirely of royalty-free audio and songs.

Optimized Stable Audio Open Model

Stable Audio Open, running on Arm chips, can generate a sound from a text description like, "Gentle ocean waves at sunset." Stability says that it worked with Arm to optimize and "distill" Stable Audio Open, speeding up generation times by 30x. Generating a single 11-second audio sample takes around 8 seconds on an Armv9 CPU.

Availability and Future Plans

The optimized Stable Audio Open model is not available for download yet. However, in a statement, Stability CEO Prem Akkaraju hinted that Stability will work to bring its models, including Stable Audio Open, to consumer apps and devices in the future.

Collaboration with Arm

Stability is collaborating with Arm to further optimize and fine-tune Stable Audio Open for mobile devices.

Company Background

Stability, the company behind the popular image generation model Stable Diffusion, raised new cash last year as investors, including Eric Schmidt and Napster founder Sean Parker, sought to turn the business around. The company has since hired a new CEO and appointed Titanic director James Cameron to its board of directors, and has released several new image generation models.

Conclusion

The partnership between Stability and Arm brings AI-powered audio generation to mobile devices, offering a more accessible and convenient way to create high-quality audio content. With its optimized Stable Audio Open model, Stability is poised to revolutionize the way we experience audio on the go.

Frequently Asked Questions

Q: What is Stable Audio Open?
A: Stable Audio Open is an AI model that can generate audio, including sound effects, from a text description.

Q: What is the training set of Stable Audio Open composed of?
A: The training set of Stable Audio Open is made up entirely of royalty-free audio and songs.

Q: How fast is the optimized Stable Audio Open model?
A: The optimized Stable Audio Open model can generate a single 11-second audio sample in around 8 seconds on an Armv9 CPU.

Q: When will the optimized Stable Audio Open model be available for download?
A: The optimized Stable Audio Open model is not available for download yet, but Stability plans to bring its models to consumer apps and devices in the future.