the AI Hardware Partner
Toggle Nav

Coral USB Accelerator


Coral USB accelerator is a USB accessory that brings machine learning inferencing to existing systems. Works with Raspberry Pi and other Linux systems.

In stock


Coral USB accelerator is a USB accessory that brings machine learning inferencing to existing systems. Works with Raspberry Pi and other Linux systems.


  • Performs high-speed ML inferencing: High-speed TensorFlow Lite inferencing with low power, small footprint, local inferencing

  • Supports all major platforms: Connects via USB 3.0 Type-C to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10

  • Supports TensorFlow Lite: no need to build models from the ground up. Tensorflow Lite models can be compiled to run on the edge TPE
  • Supports AutoML Vision Edge: easily build and deploy fast, high-accuracy custom image classification models at the edge. 

  • Compatible with Google Cloud


The on-board Edge TPU is a small ASIC designed by Google that accelerates TensorFlow Lite models in a power-efficient manner: it's capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. For example, one Edge TPU can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 frames per second. This on-device ML processing reduces latency, increases data privacy, and removes the need for a constant internet connection.

This allows you to add fast ML inferencing to your embedded AI devices in a power-efficient and privacy-preserving way. Models can be developed in TensorFlow Lite and then compiled to run on the USB Accelerator.



AI-enabled NVR system

If you are planning to use Coral USB Accelerator for Home Assistant of home automation applications, we recommend Odyssey Blue, an Intel Celeron J4125 powered X86 Windows/Linux mini PC, you can set them together with ip cameras for a local AI processed NVR system. 

Frigate is a completely open source and local NVR designed for Home Assistant with AI-powered object detection. It uses OpenCV and Tensorflow to perform real-time object detection locally for IP cameras. It brings a rich set of features including video recording, re-streaming, and motion detection, and supports multiprocessing. 

Code examples and project tutorials to build intelligent devices with Coral

Object tracking with video

This example takes a camera feed and tracks each uniquely identified object, assigning each object with a persistent ID. The example detection script allows you to specify the tracker program you want to use (the Sort tracker is included).

View on GitHub

Image recognition with video

Stream images from a camera and run classification or detection models with the TensorFlow Lite API. Each example uses a different camera library, such as GStreamer, OpenCV, PyGame, and PiCamera.

View on GitHub

PoseNet pose estimation with video

Use the PoseNet model to detect human poses from images and video, such as locating the position of someone’s elbow, shoulder, or foot.

View on GitHub


System requirements 

  • A computer with one of the following operating systems:
    • Linux Debian 10, or a derivative thereof (such as Ubuntu 18.04), and system architecture of either x86-64, Armv7 (32-bit), or Armv8 (64-bit) (Raspberry Pi is supported, but we have only tested Raspberry Pi 3 Model B+ and Raspberry Pi 4)
    • macOS 10.15, with either MacPorts or Homebrew installed
    • Windows 10
  • One available USB port (for the best performance, use a USB 3.0 port)
  • Python 3.5, 3.6, or 3.7

 Tech Specs

ML accelerator

Google Edge TPU coprocessor:

4 TOPS (int8); 2 TOPS per watt


USB 3.0 Type-C* (data/power)


65 mm x 30 mm


US, Austria, Australia, Belgium, Bulgaria, Croatia, Cyprus, Denmark, Estonia, Finland, Germany, Ghana, Greece, Hong Kong, Hungary, Iceland, India, Indonesia, Ireland, Israel, Italy, Japan, Kenya, Latvia, Liechtenstein, Lithuania, Luxembourg, Malaysia, Malta, Netherlands, Norway, Oman, Philippines, Poland, Portugal, Romania, Singapore, Slovakia, South Korea, Spain, Sweden, Switzerland, Thailand, Turkey, United Kingdom, Vietnam


Part List

1 x Coral USB Accelerator


HSCODE 8471800000
USHSCODE 8471410150
EUHSCODE 8471707000
CE 1
EU DoC 1
RoHS 1





Write Your Own Review
Only registered users can write reviews. Please Sign in or create an account
  1. Documentation
    Product Quality
    from order view
    The product has arrived quickly, and seems ok. I've tried to make it work in windows, following the documentations but couldn't. It seems some packages (and dependencies) used with Coral TPU are quite outdated. Maybe an update of Python to 3.12 with all dependencies would be welcomed.
  2. Documentation
    Product Quality
    from order view
    Good build quality and a great price! Cheapest I could find it anywhere and it was actually in stock!
  3. Documentation
    Product Quality
    from order view
    Perfect product, best price, timely shipping, great communication, five-star experience.. SeeedStudio is now my go to for all things IoT.
  4. Documentation
    Product Quality
    from order view
    The Coral USB Accelerator has elevated my Home Assistant setup remarkably. Its powerful performance boost is evident in tasks like AI processing for security cameras and energy optimization. Integration with Home Assistant is seamless, and its compatibility with various platforms adds flexibility. This compact device is a game-changer for smart homes, offering exceptional speed and ease of use. Coral has delivered a top-notch product for home automation enthusiasts, unlocking new possibilities in the realm of smart homes.

    Pros: High-performance enhancement, seamless Home Assistant integration, platform compatibility, compact design.

    Cons: None observed so far.

    The Coral USB Accelerator is a must-have for any smart home enthusiast seeking to revolutionize their Home Assistant projects.
  5. Product Quality
    from product detail summary
    Product works great. Was able to pick one up shipped in a reasonable time period and was able to quickly get started using it for my projects. Would highly recommend grabbing one of these to play around with.


Items 16 to 20 of 32 total

Show per page