Stable Audio Open Small is a 341 million parameter text-to-audio model optimized to run entirely on Arm CPUs. It is designed for quickly generating short audio samples and can produce up to 11 seconds of audio on a smartphone in less than 8 seconds. This model is a compact variant of the industry-leading text-to-audio model Stable Audio Open, and it preserves output quality and prompt adherence while being smaller and faster.
Stable Audio Open Small is the fastest stereo text-to-audio model on the market, with a lightweight architecture that has 341M parameters compared to Stable Audio Open's 1.1B parameters. It is optimized to generate audio on a mobile phone in less than 8 seconds and is faster to generate and fine-tune. The model is also efficient, leveraging Arm's KleidiAI libraries to run even more efficiently at the edge, providing faster results while lowering costs for compute time.
Stable Audio Open Small is well-suited for generating short audio samples, sound effects, and production elements using text prompts. It is perfect for creating drum loops, foley, instrument riffs, and ambient textures. The model's compact size and fast inference make it a great fit for on-device deployment on Arm-powered smartphones and edge devices, where real-time generation and responsiveness matter. By using different model sizes, organizations can allocate workloads to the processors best suited to their use case.
Get more likes & reach the top of search results by adding this button on your site!
Get top updates in AI to your inbox every weekend. It's free!