Stability AI and Arm Launch On-Device Audio Model

May 15, 2025
Stability AI, in collaboration with Arm, has released Stable Audio Open Small, an audio-generating AI model optimized for smartphones, enabling offline audio generation.

Stability AI has released Stable Audio Open Small, an audio-generating AI model that can run on smartphones, announced on their website. This model, developed in collaboration with Arm, is designed to generate short audio samples and sound effects efficiently on mobile devices.

Stable Audio Open Small is a compact model with 341 million parameters, optimized to run on Arm CPUs. It can produce up to 11 seconds of audio on a smartphone in less than 8 seconds. Unlike many AI-powered apps that rely on cloud processing, this model allows for offline audio generation, making it accessible without heavy hardware requirements.

The model's training set consists entirely of royalty-free audio from Free Music Archive and Freesound, reducing intellectual property risks. However, it only supports English prompts and is limited in generating realistic vocals or high-quality songs. The model is available for free under the Stability AI Community License for commercial and non-commercial use, with certain restrictions for larger businesses.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.