Synaptics launches Astra SR200 chips with Google Coral NPU

Synaptics has introduced the Astra SR200 Series, launching a class of microcontrollers it calls xMCU for multimodal edge AI. The chips combine heterogeneous compute and AI acceleration with integrated high-bandwidth custom DRAM scalable to hundreds of megabytes. The design is intended to overcome the memory and processing limits of conventional microcontrollers, allowing larger AI models and richer multimodal workloads to run entirely on-device. Target applications include AI wearables, battery-powered sensing devices, connected cameras, streamers, and industrial vision and voice systems.

The processors use the Synaptics Torq AI engine, featuring the Coral NPU from Google Research within a standards-based hardware architecture and unified developer environment. The series also pairs Arm Cortex -M85 and Cortex -M52 cores, alongside integrated vision and audio capabilities and hardware-rooted security. Synaptics positions the combination as a way to improve system design efficiency and reduce costs for edge and physical AI devices.