On-device audio generation on smartphones is now possible with Arm, drastically reducing generation time!
Stability AI and Arm Bring On-Device Generative Audio to Smartphones
Original: Stability AI and Arm Bring On-Device Generative Audio to Smartphones — Stability AI
Importance: スマートフォン向け音声生成技術の新しい展開は多くのユーザーに影響を与えるため。
Summary
Stability AI partners with Arm to enable on-device generative audio on smartphones. This allows for high-quality sound effects and audio samples to be created without an internet connection. The technology has reduced audio generation time from 240 seconds to under 8 seconds on Arm CPUs and will be showcased at MWC Barcelona in March 2025.
Key Points
- Partnership with Arm enables audio generation
- Works offline without internet connection
- Generation time reduced from 240s to 8s
- Showcase planned at MWC Barcelona
- Plans to extend to other media types
View developer notes (APIs, breaking changes, migration)
Stability AI optimized its Stable Audio Open model for mobile in collaboration with Arm, achieving a 30x speed increase for audio generation on Arm CPUs, reducing time from 240 seconds to under 8 seconds for an 11-second clip. This allows for offline audio generation on mobile devices, with plans to extend this capability to other media types.
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.