Comments on: Collaboration focuses on multimodal AI design

Renesas and Syntiant have joined forces to enable low-power, voice-controlled operation of embedded vision AI systems in IoT and edge applications. The reference design combines the Renesas

RZ/V series

vision AI microprocessor and the multimodal Syntiant


neural decision processor. Together, they bring always-on functionality with quick voice-triggered activation from standby mode to perform object recognition, facial recognition, and other vision-based tasks.

The multimodal architecture allows the creation of contactless user experiences for vision AI-based systems, such as self-checkout machines, security cameras, and smart appliances. Using a dedicated, power-efficient chip for voice recognition reduces standby power consumption. And it is possible to develop software independently of the vision AI functionality.

The Renesas RZ/V2M microprocessor employs a dynamically reconfigurable AI accelerator that achieves high AI inference performance and an image signal processor that supports 4k 30 frames/s. Its power efficiency eliminates the need for heat dispersion measures, such as heat sinks and cooling fans. Syntiant’s NDP120 chip is a special-purpose processor for deep learning. Packaged with the Core 2 neural network inference engine, the NDP120 can run multiple applications simultaneously, while minimizing power consumption to 1 mW of battery power.

The voice-controlled multimodal AI reference design is available now, including circuit diagrams and bill of materials.

Reference design product page

Renesas Electronics


Find more datasheets on products like this one at

, searchable by category, part #, description, manufacturer, and more.