Train and deploy edge devices in the cloud. High accuracy, low power AI for keyword spotting.

Stay tuned for additional audio and signal processing applications.

Sign up for beta
Interior view of a car dashboard, featuring the steering wheel and a navigation screen.


Training and deploying models for edge devices can be complicated and time-consuming, as each piece of hardware has its own advantages, limitations, and implementation quirks. But NengoEdge, ABR’s no-code full stack software, is here to help. Just upload your data, select your hardware, test, and deploy.

High accuracy

NengoEdge can achieve state-of-the-art accuracy on keyword spotting and other tasks. This is thanks in part to our LMU algorithm, which is provably optimal for compressing and representing time series data. We also utilize a technique called Hardware Aware Training to fine-tune your model based on your target hardware platform.

Low power

Our LMU algorithm allows us to do more with less, which is great for constrained resource settings. We can get you high accuracy at low power, with less data and smaller models. From here, NengoEdge can help you explore different models and hardware, together with their trade-offs between accuracy and power, to find your ideal combination.

Low latency

The LMU’s optimality ensures quick computation. Furthermore, NengoEdge models are designed to be deployed in a streaming fashion. This means new data can be processed as soon as it becomes available. It doesn’t need to be buffered on the device, so there is no delay between audio input and model inference.

Easy to use

NengoEdge provides a simple and straightforward interface which lets you control what matters while it takes care of device-specific implementation under the hood.

See below for video introductions to NengoEdge


Keyword Spotting
The first area of application for NengoEdge is keyword spotting. You can use our software to add voice commands to your application, and detect keywords in a stream of audio data.

We are hard at work extending NengoEdge for more voice-based and digital signal processing applications. Stay tuned for updates!
Automatic Speech Recognition
Process speech, turn it into text
Natural Language Processing
More conversational human-machine interaction
Dialogue Management
Analyze flow of conversation
Convert written text into spoken words
Background Noise Filtering
Minimize any disruptive sounds
Speaker Identification
Distinguish one speaker from another
Convert text or speech from one language to another
Signal Classification
Categorize inputs based on their characteristics.
Anomaly Detection
Identify unusual patterns in your signal.
Noise Reduction
Filter out disruptive inputs.
Predictive Maintenance
Anticipate need for upkeep and repairs.

Talk to our sales team

Learn more about how low power edge computing can support your AI integration.
Contact us