What you need to know
- Amazon's AZ1 is a machine learning processor that allows for faster interactions with Alexa.
- The custom silicon allows for on-device processing of common queries — without the intervention of the cloud.
- Amazon is touting 2x faster speech processing and up to 85% lower memory usage thanks to the AZ1.
- The custom chipset is baked into the Echo and Echo Show 10.
Amazon has introduced the AZ1 Neural Edge machine learning processor that is baked into its latest products. The AZ1 is a custom processor built in collaboration with MediaTek, and Amazon is positioning it as a key differentiator in making Alexa faster.
Amazon says the AZ1 is an "all-new silicon module that's purpose-built for accelerating machine learning applications." The AZ1 silicon offers an all-neural speech recognition model that processes requests faster, making Alexa significantly faster — Amazon says it was able to reduce hundreds of milliseconds per response, which is a huge deal.
Amazon says the AZ1 offers best-in-class energy efficiency with up to 20 times less energy usage, 2x faster speech processing, and 85% lower memory usage. AZ1 is able to deliver these improvements because the processing itself is being done on-device, cutting out the need for your query to be sent to the cloud. Basically, the addition of the AZ1 allows for common queries like turning off the lights to be processed on the device directly, leading to significantly faster interactions.
The AZ1 is built into the latest-generation Echo products, including the new Echo and Echo Show 10. The improved interactions will be available initially to English users in the U.S., with other languages and markets added at a later date.
We may earn a commission for purchases using our links. Learn more.