Syntiant  Always-On Sensor & Speech Recognition Processors



NDP101 Neural Decision Processor™

The Syntiant® NDP architecture is built from the ground up to run deep learning algorithms. With embedded Syntiant Core 1™, the NDP101 achieves breakthrough performance by highly coupled computation and memory, exploiting the vast inherent parallelism of deep learning and computing at only required numerical precision. The devices combine these elements to achieve approximately 100x efficiency improvement over stored program architectures such as CPUs and DSPs. 


Keyword Speech Interface

Created from the simultaneous classification of dozens of keywords

Ease of Use

Multiple, flexible methods to access neural processing engine where the user has full customization of applications and post-processing

Ultra-Low-Power Consumption

Micro-watt level active power consumption, while always-on and listening



Programmable general purpose IO, SPI Master and ability to boot from a serial flash enabling the NDP100 to be the only processor in the system

Neural Processing

Neural network with over half a million parameters providing large scale parallelism for sensor-based applications


The NDP101 enables speech interfaces in the smallest systems, replacing traditional tactile interface elements (buttons, switches and dials) and supporting entirely new form factors and usage models designed to wake up to speech rather than touch. 

mobile phones • smart home • remote controls • smart watches • IoT endpoints

media streamers.png
iot endpoint .png

Key Features

+    System on chip in a 32 pin QFN package


+    Suitable for applications that require an MCU for control and a neural engine for decision making


+    Dual PDM microphone input or PCM-over-SPI input


+    Stereo/mono I2S interface multiplexed with PDM


+    Direct access to neural network over SPI for sensor applications


+    Frequency, time-domain & batch input models


+    16-bit input holding tank with faster than real-time SPI extraction


+    Embedded Arm Cortex-M0 processor with 112KB SRAM

+    Eight GPIO pins with programmable direction and drive strength  

+    Support for external serial flash boot

+    Integrated clock multiplier and dividers support low-frequency clock source or external clocking


+    Optimized interrupt and SPI slave interface


+    Master SPI interface for sensor interfaces


+    Onboard firmware security and authentication


+    English speech service for keyword training


+    Software Development Kit (SDK) integrates in any software environment


+    Training Development Kit (TDK) to enable the use of standard frameworks such as TensorFlow for customer-programmed applications


+    Support for 64 output classifications


+    Active power consumption of <140µW while recognizing words