latentbrief
Back to news
Launch1h ago

Google's AI Edge Breakthrough for On-Device Audio Generation

blog.google1 min brief

In brief

  • Google has unveiled a major advancement in on-device AI processing, enabling high-quality audio generation directly on mobile devices.
  • Their new system uses Arm Scalable Matrix Extension 2 (SME2), which boosts CPU performance for AI tasks by up to 5x.
    • This breakthrough simplifies deploying complex models like Stability AI’s stable-audio-open-small, allowing developers to create 11-second stereo clips from single prompts without low-level coding.
  • The integrated Google AI Edge stack streamlines the process with tools like LiteRT-Torch and AI Edge Quantizer, making it easier to optimize and deploy models on Arm CPUs.
    • This innovation opens doors for personalized, real-time audio experiences on mobile devices, marking a significant step forward in edge AI capabilities.

Terms in this brief

Arm Scalable Matrix Extension 2 (SME2)
A technology that enhances CPU performance for AI tasks by up to five times. It's designed to improve on-device processing capabilities, making high-quality audio generation possible directly on mobile devices.
LiteRT-Torch
A tool within Google's AI Edge stack that simplifies the process of optimizing and deploying AI models on Arm CPUs. It helps developers create audio clips from single prompts without needing low-level coding skills.
AI Edge Quantizer
A component of the Google AI Edge stack used to optimize AI models for deployment on edge devices, such as mobile phones. It ensures that complex models can run efficiently on hardware with limited processing power.

Read full story at blog.google

More briefs