lisa@proknx.com, Author at Hey Aragon

Are you ready for a home that knows what you want before you do?

Imagine walking into a room in your smart home. The temperature is perfect, the lights turn on before you get there, and your favourite music is playing in the background. You feel instantly comfortable. It seems like magic! How does your smart home system know what you want without any prompts from you? Read on to find out.

Intelligent presence prediction is the umbrella term for the seemingly magic anticipatory abilities of modern smart home products. The devices are able to ‘know’ what the user wants before they even know it themselves with two different, but complementary methods.

Nowcasting: The “Here and Now”

Nowcasting is about understanding what’s happening right now. Your motion sensors detect you’re in the room. Your door sensor shows you just arrived home. This is real-time intelligence—instant and reactive. It’s perfect for immediate actions like turning on lights when you enter a space or adjusting temperature the moment you wake up.

Think of it as your home paying attention in the present moment.

Forecasting: The Smart Prediction

Forecasting goes further. It learns your patterns and predicts what you’ll want before you need it. Based on your daily habits, calendar, location history, and preferences, your home anticipates your next move. Your thermostat warms up 15 minutes before you typically arrive home. Your bedroom lights dim automatically on Friday evenings because your home knows your weekend routine.

It’s not reacting—it’s thinking ahead.

Why Does This Matter?

While nowcasting keeps your home responsive and safe, forecasting transforms it from a reactive system into a truly anticipatory one. This means:

✦ Better comfort: No more entering a cold home or dark rooms
✦ True energy efficiency: Systems optimize before you arrive, not after
✦ Seamless experience: Your home feels like it understands your lifestyle
✦ Reduced friction: Fewer manual adjustments needed

The Future of Home Automation

The most advanced smart homes combine both approaches. They react instantly to what’s happening now while simultaneously predicting what comes next. It’s the difference between a home that responds to you and a home that anticipates you.

The line between convenience and intelligence is getting thinner. Are you ready for a home that doesn’t just react—but predicts?

Spotify on Aragon – A Technical Overview

Spotify Voice Control use on Sonos via Aragon Maestro

Introducing Aragon Maestro’s new feature for controlling Spotify playback on Sonos speakers! This new solution is engineered with a privacy-first, offline-focused approach that leverages on-device processing for all sensitive actions. How does Aragon process the request? Read on to find out.

System Architecture and Data Flow

The control sequence from voice command to music playback is executed primarily on the local network, minimizing external communication.

Voice Data Acquisition: A local network Aragon Satellite (WL or PoE) captures the user’s voice command requesting certain music. The raw audio data is streamed directly to the Aragon Maestro over the local network.
On-Device Speech-to-Text (STT): Aragon Maestro processes the incoming audio stream using the on-board Whisper ASR model for speech-to-text conversion. This entire transcription process occurs locally on -device with no voice data sent to the cloud.
On-Device Natural Language Processing (NLP): The resulting text string is fed into a local, on-device Large Language Model (LLM). This AI-driven model interprets the command, identifying the user’s intent, e.g., play, pause, skip, and the relevant information needed to carry out the command , e.g., artist name, song title, playlist. This allows the system to understand complex, natural language queries without relying on predefined vocabulary or cloud-based NLP services.
Spotify API Interaction: Once the request is understood, the Aragon Maestro makes a targeted, anonymous query to the Spotify API. This is the only point of contact with an external cloud service. The purpose is strictly to enumerate tracks, albums, or artists based on the user’s request, and to retrieve the necessary identifiers for playback. No user-specific or personally identifiable information is transmitted by the Aragon system in this query.
Local Sonos Control: Using track information from Spotify, the Maestro issues a command directly to the Sonos speaker(s) over the local area network (LAN). This instructs the Sonos system to stream the selected media directly from Spotify’s servers.

Key technical differences between Aragon and generic smart speakers

Private-by-Design: The entire voice processing pipeline (STT and NLP) is self-contained within the Aragon Maestro, ensuring user voice commands are never exposed to the internet.
Local Network Operation: All communication between Aragon Satellites, the Aragon Maestro, and the Sonos speakers occurs on the local network.
Minimal Cloud Footprint: The only external communication required is a stateless, anonymous request to the Spotify API for discovering music. There is no constant connection or data exchange with Aragon-hosted cloud services.
Integrated AI: The use of on-device Whisper and LLM technologies provide advanced, flexible voice control without need for an internet connection to process commands

Use cases for the new Sound Event Detection Feature

Recently, we launched Aragon Maestro’s all-new Sound Event Detection (SED) feature. The graph of detected sounds is pretty to look at, but what can the detection of these sounds be used for?

Imagine that you are not at home. Suddenly, your smart-home system sends an alert to your phone. It has registered sounds of breaking glass, doors or cupboards opening and closing, and/or footsteps. You know that the house should be empty. A quick call to the police, and the burglar is caught red-handed!

Now think about your elderly mother who is at home alone. She has been ill recently with a bad cold, but she doesn’t like to worry you about how she is feeling. The sounds of incessant coughing are detected over a few days. Time to have the doctor in before her health deteriorates further!

The SED feature also picks up whether TV or radio have been left on, and if the beloved dog or cat of the inhabitant barks or meows intensively for a prolonged time. Detection of regular day sounds such as flushing toilet and running water noises are also important. The presence or absence of these sounds raise an alert that the user needs to be checked on, to make sure that they are in good health.

The usefulness of each detectable acoustic event logged by the sound event detection feature can be personalized for individual users, with alerts sent out when the absence, or presence, of particular sounds are pinpointed.

In the Future:

From this strong foundation we plan to develop more useful features in the future, such as

– detecting the presence or absence of users to automate certain smart appliances

– detecting abnormal sound patterns when users are away from home to increase security

Watch this space for new Aragon Maestro developments!

Aragon Maestro Leads the AI-Driven Smart Assistant Market

We are pleased to announce the release of our new smart speaker, Aragon Maestro, a high-quality smart-home assistant with many new features that significantly enhance its overall capabilities. The Aragon Maestro puts offline home automation control on a whole new level with the on-device addition of AI-driven personal assistance features. This world-first represents an important advancement in voice control for home automation.

We have built on the success of our previous Aragon Master smart speaker to develop the next-generation Maestro. The product retains all its predecessor’s essential features, including on-board Node-RED and remote connection, coupled with a host of new AI-driven personal assistance features that function on-device.

Aragon Maestro Functions Without the Cloud

The Aragon Maestro fills a gap in the smart-home market for a fail-safe smart speaker that functions in all situations, including in areas of poor connectivity. The Maestro’s independence from the Internet allows the users reliable and secure control of the smart environment. Consequently, this infallibility is of the utmost importance in use cases where the device is giving autonomy to disabled people, or to seniors living alone.

Exciting New Speech-To-Text Technology

The assistant understands complex queries without training on set vocabulary, thanks to reworked speech-to-text technology of the Aragon Maestro. This is due to the integration of an on-device LLM (Large Language Model). Therefore, the unit easily adapts to a wide variety of specific user requirements. This a necessary feature in smart solutions for senior- and disabled-care. The new technology opens up the sector to OEM for integrators or companies looking to offer bespoke smart solutions.

We have also made significant improvements in the Aragon Maestro’s capacity to understand wake-words and commands. The hybrid text-to-speech on-device system of Kaldi and Whisper technologies augment the capability of the smart speaker to understand commands. In addition, this holds true even in noisy environments.

As an additional feature, a to-do list can now be generated on-device. Although independent of cloud functionality, the list can be accessed remotely through an encrypted point-to-point remote connection.

High Interoperability

The Aragon Maestro is interoperable with a wide variety of standards. The product primarily controls KNX systems, however any IP is supported with some development. This facilitates the addition of the smart speaker into a large range of intelligent environments. The device is ready for installation in private homes, residential facilities, offices, and hotels.

The Aragon Maestro smart speaker is currently available for the English language. A progressive release is expected in Q3 of French and German models.

For more detailed information on the Aragon Maestro: https://heyaragon.com/product/aragon-maestro-en/

Theben LUXORliving, Future-Shape, and ProKNX together at The L+B Show in March

Come and see future-proofing in action at the Light + Building Trade-show!

In the spirit of our new cooperation with Theben AG and Future-Shape GmbH, we will be joining the two companies at the Theben booth at The Light + Building Trade Fair from 3 – 8 March in Frankfurt, Germany. There, we will demonstrate an extraordinary development that will change the way smart home solutions are designed to encompass future living needs, as well as present ones.

Look out for us at Hall 12, Stand B50 at the biggest trade fair stand in Theben’s history!

Click here for information on the L&B show.

Theben LUXORliving training case makes for easy integration

We are finalizing the integration of our Aragon smart speaker with the LUXORliving smart home solution by Theben. The process of integration with Theben AG LUXORliving is going very smoothly thanks to their training case!

Using this training case has made the testing phase simple and straight-forward.

Theben’s portable training case contains twelve LUXORliving products used for training when integrating smart devices into the solution. A display of lights and LED panels show events that occur during testing, thus giving a clear vision of the results.

In using the case, we have determined that our Aragon system integrates smoothly with the LUXORliving server IP1.

Once the needed home automation features are defined in the LUXORplug application and transferred, the Aragon smart speaker automatically reads any room names, device names, and types from the IP1 server.

This integration will support a large number of home automation products, from lighting and dimmers, to shutters and scenes.

Download a free brochure below:

Brochure DE Theben + ProKNX Download

Aragon 1.5 – What’s new?

Aragon Version 1.5 – get ready to be amazed!

We have been working tirelessly over the last months to add to the capabilities of our Aragon Master! In this article we discuss the new features that have just been released.

The Aragon Master will soon have enhanced abilities, from ability to be interoperable with the majority of smart-home systems, to having the latest documentation at your fingertips, to optimizing voice commands to fine-tune individual devices to perfectly suit the end-user.

1. Homebridge Integration

One of the most important new features of our Aragon Master allows interoperability with any smart-home standard, from the already established KNX standard, to Matter, or the Apple Homekit.

Homebridge has been developed by a large number of plugin developers and core contributors. It allows integration of smart home devices unsupported by Apple’s Homekit into any smart home solution. Consequently, users can install Homebridge on the Aragon Master to access a slew of plugins developed for easy integration of thousands of smart appliances.

Choice in the smart-home world has suddenly become a lot larger!

For more information on Homebridge, click the link below:

https://homebridge.io/

2. Aragon documentation now integrated into the Aragon Master

Aragon Documentation and Help is now integrated on Aragon Master. This means that all the information you need is at your fingertips. On-device, you can find a mirror of up-to-date help documentation, history, and NodeRed that is also found on Github.

Watch the video below to see a demonstration of the user experience offered by the new on-device help and documentation service.

3. Voice Control Optimization

The third feature that we are very pleased to be able to bring you is Voice Command Optimization. Users can now fine-tune voice commands by excluding commands that are not useful, e.g. if the building has no shutters or blinds, the commands to control them can be removed.

The user can also select from various models of assistants with different sets of commands from “large”, to “medium”, to “tiny”. An advantage for using a “tiny” range of commands could be for a user with unclear pronunciation. As there are fewer possibilities available, the smart speaker will be less likely to pick the “wrong” command.

4. Updated Voice Assistants

We have also done a significant amount of development in the area of Text to Speech voices that are available to the user of the Aragon smart speaker. The quality of each voice option has become greatly enhanced, which promotes better understanding for the end-user.

Additionally, the range of English-speaking voices has been markedly increased, particularly in the variety of British accents on offer. A wider choice of voices in German and French has also been added.

Shop for the Aragon Master and satellites here.

ProKNX and Future-Shape announce partnership

ProKNX and Future-Shape are pleased to announce their partnership to bring the Aragon smart speaker and innovative Sens-floor® together to create an essential smart technology solution. Working in tandem the two products will allow new safety and security measures to be put in place for people living alone, residential homes, and care-homes. This is a huge advancement for the care sector.

The special flooring from Future-Shape is a large, discreet sensor system that can be installed under any kind of flooring. The smart floor detects presence and movement of people without the need for pressure. The signals are sent wirelessly to a transceiver. The transceiver, in turn, calculates the number of people on the floor, their direction and speed, as well as detects falls.

There are multiple use-cases for Sens-Floor® coupled with the Aragon smart speaker installation. These range from health care and Assisted Living, to home automation and security.

To see how Aragon Companion and Sens-Floor® work together, watch the demonstration video below:

Node-Red can be used for the effortless integration of Sensfloor® and Aragon for any smart system installation. Generating code is simple to do by implementing a node developed by FlowFuse. The node uses AI to generate code an integrator needs to achieve interoperable functionality.

For more information on the ease of creating Node-Red code with AI to set up a smart-home solution, go to our HeyAragon developer website.

It is time to take your privacy seriously

Why we are no longer supporting Alexa

We have made a conscious choice not to ship hardware with direct support for the online voice assistants Alexa or Google Assistant.

Our Privacy Philosophy Benefits You.

We believe that:

Our customer should be able to be independent of us – cloud-based service (e.g. Alexa Skill) is a service that must be made available on an Internet server day and night. This requires an infrastructure with financial and technical support. We want to be honest with our clients, and cannot guarantee this service for the next 5, 10 or 20 years. Therefore, want to offer you a better solution for the future.
We should not have access to our customers’ installations – The skill not only allows the online voice assistant to access our customers’ installations, but also us at ProKNX, and anyone who should ever have access to our data pool. We do not want to bear this responsibility, as it is not in your best interests.
“What’s said at home, stays at home” – Our slogan is one that we truly believe in. Our development of ARAGON shows that today we are able to enable privacy and offer voice assistants offline. We refuse to support data and information theft.

Therefore, as of Sep 1, 2023, our “realKNX servers” will no longer support Alexa, Google Assistant, or remoteConnect.

What happens to the systems we have delivered so far?

For more information, go to our parent-site ProKNX

Introducing the all-new Aragon Master!

The Aragon Master, a compact, yet powerful server for voice control contains everything needed to understand your voice commands. It also ensures seamless interaction with your home automation system.

The master can work in an isolated system. All analysis of speech and execution of commands carried out on-device. As an added option, there is an “online mode”. This allows the user access to powerful online services like OpenAI/ChatGPT and Google.

The Aragon Master featured in the photograph is the Offline version. It comes with an external battery designed to support the onboard real-time clock functionality. The inclusion of the battery is optional, primarily intended for situations where your Master device lacks internet connectivity and a time server.

Find out all about the Aragon Master product specifications here

The Pyramid of Protected Privacy

Voice control with Privacy in focus

Aragon2 is our second-generation smart speaker. The original award-winning Aragon for Snips voice-controlled assistant was launched at the beginning of 2020 with the privacy of data as its primary focus.

The Aragon2 functions in an isolated network to control home automation devices, just like its predecessor, with all analysis of speech and execution of commands carried out on-device. This ensures the privacy of the user, and reliability of service.

Aragon2 differs from the original device by having augmented capabilities. When the smart speaker is in “online mode” the user has access to powerful online services like OpenAI/ChatGPT and Google.

Protected Mode – 100% Offline – Privacy guaranteed

In the Protected Mode, the Aragon system:

– Executes all home automation-related voice commands
– Speaks with a selectable voice, which also runs on the device.

But,

– Cannot update its software
– Cannot perform Network time synchronization over the Internet.

The solution: the Master is equipped with a battery to power the RTC. Additionally, all Satellites are equipped with special time synchronization software.

If you plan to run Aragon in an Internet disconnected network, add the Offline Kit to your basket.

Ideal for:

– Premises where the integrity of the users is an absolute requirement, e.g. executive meeting rooms
– Where Internet connection is limited, e.g. cruise ships and yachts.

Safe Mode – connected to the Internet

In Safe Mode, the Aragon system:

– Executes all home automation-related voice commands
– Speaks with a selectable voice, which also runs on the device.
– Uses Network time synchronization over the Internet
– Updates software at the user’s request. Additionally, Aragon
– Can optionally answer weather forecasts and traffic information queries.

No audio leaves the device, the voice commands are treated on the device (on-board ASR and NLU).

Ideal for:

– Premises where the integrity of the users is a requirement e.g. Homes, Offices, Hotels.

Trusted Services mode – Online-Offline

By adding the Trusted services, Aragon will be able to answer any query that you may ask OpenAI/ChatGPT and Google. Google search is accessed in a safe and anonymous manner via a proxy service, SerpAPI.

– ChatGPT by OpenAI is an artificial intelligence chatbot designed to engage in natural-sounding conversations. It utilizes the most advanced AI technology available today and can provide responses that are both coherent and accurate.

– SerpAPI is a powerful tool that enables access to Google and Bing search engine results pages, anonymously and with privacy.

How Trusted Service Mode Works

When the user switches to Trusted Service mode, Aragon uses an online service for transcription. This is necessary in order to understand users’ queries. The onboard Speech-to_text (or ASR) is trained and limited to Home Automation and media control tasks. To support the full English language, the audio is redirected to an external service.

The user enters online mode by saying Enter online mode and leave by saying Leave online mode. Aragon will automatically leave online mode after 1 hour of inactivity.

Before using online mode, the user must create free accounts for trusted online services.

Download your free copy of the privacy pyramid by clicking on the link below:

Aragon – Privacy by Design Download