'Stable Audio Open Small', a music generation AI that runs locally on smartphones, is released, capable of generating up to 11 seconds of audio in less than 8 seconds
Stability AI, an AI development company known for developing the image generation AI 'Stable Diffusion,' has released ' Stable Audio Open Small, ' a music generation AI that runs locally on smartphones. Stable Audio Open Small was developed in collaboration with Arm, and can generate up to 11 seconds of music in less than 8 seconds on a smartphone equipped with an Arm architecture CPU.
Stability AI and Arm Collaborate to Release Stable Audio Open Small, Enabling Real-World Deployment for On-Device Audio Generation — Stability AI
https://stability.ai/news/stability-ai-and-arm-release-stable-audio-open-small-enabling-real-world-deployment-for-on-device-audio-control
Stable Audio Open Small is developed based on the music generation AI ' Stable Audio Open ' that was released in June 2024 with 1.1 billion parameters, and the number of parameters has been reduced to 341 million. In addition, by utilizing Arm's AI acceleration library ' Kleidi ', it has become lightweight enough to run locally on a smartphone equipped with an Arm-based CPU.
Running Stable Audio Open Small on a smartphone can generate up to 11 seconds of music in under 8 seconds. An example of music generated by Stable Audio Open Small is embedded in the post below.
Today we're open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on @Arm CPUs.
— Stability AI (@StabilityAI) May 14, 2025
This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required.
Built for fast,… pic.twitter.com/LryqPlfwjj
The license for Stable Audio Open Small is the ' Stability AI Community License ', which is free for non-commercial use. It can also be used for commercial purposes for free if your annual revenue is less than $1 million (approximately 150 million yen).
The model data for Stable Audio Open Small is distributed at the following link.
stabilityai/stable-audio-open-small · Hugging Face
https://huggingface.co/stabilityai/stable-audio-open-small
In addition, Arm documentation is available at the following link:
Generate audio with Stable Audio Open Small on LiteRT | Arm Learning Paths
https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/run-stable-audio-open-small-with-lite-rt
Related Posts:
