From Earbuds to Automobiles
Syntiant is making edge AI a reality.
Our turnkey deep learning solutions bring a highly accurate, ultra-low-power AI interface to always-on image, voice, audio and sensor applications across a wide range of consumer and industrial use cases. Many machine learning workloads that typically would be run in high-powered application processors or on cloud servers can now be run in the low-power, always-on domain.
Designed by applying an extensive low-power methodology, Syntiant’s purpose-built devices offer more than 100x efficiency improvement while providing over a 10x increase in throughput compared to current low-power MCU solutions, and subsequently, enabling larger networks at significantly lower power.
Using at-memory compute and built-in standard CMOS processes, Syntiant devices directly process neural network layers from platforms such as TensorFlow without the need for any secondary compilers to shorten time to market and offer unprecedented performance for solutions that require under 1mW power consumption.
By combining purpose-built silicon with an edge-optimized data platform and training pipeline, Syntiant provides customers with low-cost, low latency, end-to-end solutions that quickly deliver production grade deep learning models in a variety of domains to enable a robust interface between the physical world and digital world, free from cloud connectivity, ensuring privacy and security.
With package sizes as small as 1.4 mm x 1.8 mm, Syntiant’s Neural Decision Processors (NDPs) enable highly accurate, ultra-low-power AI voice processing in the tiniest of devices.
By bringing high levels of neural processing into very small form factors, Syntiant devices can support wake words, voice commands, as well as noise suppression.
Our devices help build intuitive hands-free voice assistants, enabling users to easily interact with technology in their everyday lives by using speech rather than pushing buttons or touching screens, while simultaneously improving the communications experience.
Today’s connected consumer wants one thing above all else – ease of use!
From smartwatches to fitness trackers and health monitoring wristbands, Syntiant’s NDPs meet the requirements of the tiniest and most demanding low-power speech and sensor applications.
Our end-to-end solutions bring a level of machine learning to wearables previously only available at 10x the power and twice the die size.
Syntiant’s ready-to-use technology brings hand-free functionality to wearable devices, letting users access and control information free from touch, from voice commands to accelerometer and temperature control to motion detection.
The rise of AI in telemedicine is having a profound impact on how different medical conditions are screened and analyzed.
From remote patient monitoring to other diagnostics and imaging, voice and sensor applications, Syntiant’s deep learning technology serves as a powerful AI interface for next-generation medical devices.
Whether enabling a hospital patient to turn on a TV using speech, or checking a person’s vital signs at home, Syntiant’s customizable neural networks process voice and sensor data on device, faster and more reliably, ultimately helping improve patient outcomes.
And because our technology does not require a cloud connection, sensitive data can remain locally, ensuring patient privacy and security.
Consumers increasingly are opting to use speech to control their smartphones. Hands-free operation offers many benefits, from providing multilingual wake word engine and voice control to improving ease-of-use and productivity.
Syntiant’s purpose-built compute engine for neural inference solves the power consumption problem for edge AI processing, allowing audio, speech and image applications to be run in parallel with negligible drain on battery life.
Our technology also enables close talk and far-field voice applications to be executed in parallel with advanced sensor functionality and biometric speech and image recognition in the low-power, always-on domain, keeping the application processor asleep and greatly extending battery life.
No matter where a person is located, what device they are using, or even what language they speak, Syntiant’s end-to-end deep learning solutions are greatly improving functionality, safety and privacy in mobile devices.
Speech recognition and the elimination of typing improves productivity, allowing people to multitask myriad functions during their everyday lives, from making video calls to managing a business to gaming.
Syntiant’s ultra-low-power neural processors also enable devices to run biometric image and voice recognition applications locally, protecting sensitive data while ensuring privacy and security.
With support for multiple wake words such as “Alexa” and “Hey Google” and multilingual voice commands, Syntiant’s neural network technology brings a complete voice, audio and speech interface to laptops that enable highly accurate edge AI processing with minimal consumption to battery power.
Everyone wants a “smarter” and more secure home. No more fumbling and fussing with keys, remotes and touch screens improve convenience, while adding video surveillance and motion sensing can increase protection.
Syntiant’s advanced edge technology allows critical and time-sensitive decisions to be made faster, more reliably and with greater security, such as glass breaking and person detection features. Multiple voice, sound and sensor applications also can be run simultaneously at significantly low power. Low cost sensors with Syntiant devices can be placed throughout the home operating for long periods of time on only coin cell batteries.
From convenience to security, Syntiant’s Core architecture can make any dwelling a smart home or office, enabling developers to bring a powerful AI interface to a wide range of smart home applications, including video doorbells, cameras and appliances.
From dishwashers to robotic vacuum cleaners, Syntiant’s ultra-low-power neural networks bring powerful AI voice and sensor processing to all kinds of smart appliances in the home.
Voice control enables consumers to effortlessly operate appliances through speech, whether it is making an espresso or checking if there is enough milk in the refrigerator. Image and sensor conditioned-based monitoring also can track the condition of equipment to reduce servicing downtime and lower costs.
Syntiant’s technology allows developers to deliver advanced voice and image processing capabilities, offering expanded functionally in today’s smart appliances while improving energy efficiency and ease of use.
The integration of artificial intelligence with Industrial IoT has had a profound impact on many diverse industries, ranging from aviation to manufacturing to transportation.
Adding sensors to critical equipment will elevate any workspace or facility. Syntiant's technology can continuously monitor sounds, vibrations and temperature to detect and act on any issues before a costly downtime failure occurs.
From condition-based monitoring to predictive quality control, Syntiant’s deep learning sensor technology provides customers with a higher degree of automation that improves performance, productivity and efficiency across a wide range of industrial and manufacturing applications.
IIoT // Condition Based Monitoring
With minimal energy consumption, automobiles can sit for long periods of time on a 12V battery while taking advantage of powerful always-on artificial intelligence.
Syntiant’s highly flexible, ultra-low-power deep neural network inference engine also can run multiple applications simultaneously at significantly lower power, from people monitoring, intrusion detection and voice-controlled infotainment systems.
Whether it is customized wake word support with a voice command module or enhanced motion sensor security features, Syntiant’s always-on technology is making automobiles secure and more connected to drivers.