Synaptics launches AI chips for wearables on Google's open Coral design
Representative image: fancycrave1 / Pixabay
Synaptics announced Astra SR200 AI chips for wearables and devices on October 20, 2026, built on Google's open Coral NPU, with 200 to 400 GOPS.
What Happened
Chipmaker Synaptics announced the Astra SR200 series on Tuesday, October 20, 2026, a family of three low-power processors for AI wearables, cameras and industrial devices built around Google's open-source Coral NPU design. The chips, named SR210, SR230 and SR250, deliver between 200 and 400 billion AI operations per second, according to the company. Google said in a developer blog that the chips have been taped out, the final step before manufacturing, while some reports said they are still being sampled with no prices or volume timetable announced.
Key Facts
- The chips: Synaptics Astra SR210, SR230 and SR250, three pin-compatible processors announced on October 20, 2026.
- AI performance: about 200 GOPS (billion operations per second) for the SR210, 300 GOPS for the SR230 and 400 GOPS for the SR250, according to the company.
- Inside: Google Research's Coral NPU (neural processing unit), Synaptics' own Torq AI engine, and Arm Cortex-M85 and Cortex-M52 processor cores, with up to 8 MB of on-chip memory.
- Uses: AI wearables, battery-powered sensors, connected cameras, streaming devices, and industrial vision and voice systems.
- Roles: the SR210 targets always-on voice and sensing at low power; the SR230 adds vision and display features; the SR250 is the most powerful.
- Developer kit: a board called Coralboard SR is available for engineers to build on the chips.
- Availability: Google's blog said launch was due this month; another report said the chips are sampling, with prices and production dates not disclosed.
Why It Matters
Most people think of AI as something that runs in huge data centres. But a growing share of AI tasks, such as recognising a voice command, spotting movement on a camera or tracking health signals on a watch, need to run directly on small devices. This is called edge AI. Running AI on the device saves battery, works without an internet connection and keeps personal data from leaving the device.
To do that, small devices need special circuits. A neural processing unit, or NPU, is a part of a chip designed to run AI models efficiently, much as a graphics chip is designed for images. Google's Coral NPU is an open design, which means chip companies can build it into their products without creating their own AI engine from scratch. Synaptics combining it with its own engine and standard Arm cores shows an open design being adopted in commercial chips.
The numbers are small compared with data centre chips, which perform trillions of operations per second, but they are what matters for a watch or a camera that must run for days on a small battery. Choosing between the three chips lets device makers balance power use against capability.
For India, which has a growing electronics design and manufacturing base and many companies building wearables, smart cameras and industrial sensors, more off-the-shelf AI chips with open designs can lower the cost of adding AI features to locally designed products. Claims about speed and power use are the company's own and will need testing in real devices.
| Chip | AI performance (company figure) | Main focus |
|---|---|---|
| SR210 | 200 GOPS | Always-on voice and sensing |
| SR230 | 300 GOPS | Adds vision and display |
| SR250 | 400 GOPS | Highest performance in the series |
Impact
Short-term: Device makers can start evaluating the chips and the Coralboard SR developer kit. Commercial products using them will take longer to reach shops.
Long-term: If open NPU designs like Coral are widely adopted, more everyday devices could run AI locally, with benefits for battery life and privacy, and more competition among chip suppliers.
Who is affected: Makers of wearables, cameras and industrial equipment, engineers building edge AI products, Google's Coral project, and consumers who buy smart devices.
Key Takeaway
Synaptics announced its Astra SR200 chips on October 20, 2026, bringing Google's open Coral NPU design to low-power AI wearables and devices, with 200 to 400 billion AI operations per second.
Questions and Answers
What is the Synaptics Astra SR200 series?
It is a family of three low-power processors, SR210, SR230 and SR250, announced on October 20, 2026 for AI wearables, cameras and industrial devices. They use Google's open-source Coral NPU design alongside Synaptics' Torq AI engine and Arm cores.
What is an NPU?
A neural processing unit is a part of a chip designed to run artificial intelligence models efficiently, using less power than a general-purpose processor for the same AI task.
What is edge AI?
Edge AI means running AI directly on a device, such as a watch or camera, instead of sending data to a distant data centre. It can save battery, work offline and keep personal data on the device.
When will the Synaptics SR200 chips be available?
Google's developer blog said they were launching this month, while another report said they are being sampled and that prices and production dates have not been disclosed.
Disclaimer: Prepared by the Peepals newsroom from publicly available sources with AI assistance. Information is accurate to the best of our knowledge at the time of publication and may change. Images may be representative. Not professional advice. Report an error via our contact page.
Sourced and fact-checked by the Peepals Global Editorial Team
Reported, fact-checked and published by the Peepals Global Editorial Team.
