New 341M parameter model generates short audio in under 8 seconds from smartphones!
Stability AI and Arm Launch Stable Audio Open Small for On-Device Audio Generation
Original: Stability AI and Arm Collaborate to Release Stable Audio Open Small, Enabling Real-World Deployment for On-Device Audio Generation — Stability AI
Importance: 新モデルのリリースが多くのユーザーに影響を与えるため。
Summary
Stability AI, in partnership with Arm, has released Stable Audio Open Small as open-source. This 341 million parameter text-to-audio model is optimized to run on Arm CPUs, allowing smartphones to generate short audio in under 8 seconds. The new model specializes in quickly generating short audio samples like sound effects and drum loops.
Key Points
- 341M parameter compact model
- Generates audio in under 8 seconds on smartphones
- Free for commercial and non-commercial use
- Optimized for Arm CPUs
- Ideal for generating short audio samples
View developer notes (APIs, breaking changes, migration)
Stable Audio Open Small is a 341M parameter text-to-audio model optimized for Arm CPUs. It generates short audio samples quickly, producing up to 11 seconds of audio in under 8 seconds on smartphones. Leveraging Arm's KleidiAI libraries, it offers efficient edge processing. It is available for both commercial and non-commercial use for free.
Outlet: Stability AI
This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.