For more information feel free to contact me


Voice UI (VUI)

Voice UI (VUI)

Ok, calling don’t call now.

“No, set the alarm to 8 AM”

OK, calling Don’t call, now

“No, no, no don’t do that!!!”

I’m sorry I cannot help you with that yet.

Phone ringing…

How many of you can relate to this?

Our voices are diverse, complex and variable. Voice commands are even more difficult to process, while we are accustomed to using our voices to get what we want from one another, the ability to get what we want from our products, in the same way, is still a relatively new phenomenon.


VUI and the new ages


User interface per se is used since the birth of the internet as we all know technology has come a long way since then.

Who cannot remember the long-gone days when we needed 2 or 3 floppy disks to copy a song from our friend? Kids today will know of the floppy disk only because it resembles the save icon.

Because of the fast development of technology, our needs started to grow, and we want faster and cheaper solutions for our day-to-day problems.

For sat need voice devices were manufactured, of course, it helps a lot in the accessibility department; making it easier for people with different disabilities to feel more included in our society.

Voice UI doesn’t resume only to the popular devices manufactured by Apple, Google and Amazon, whether we are talking about VUIs (Voice User Interfaces) for mobile apps or smart home speakers, voice interactions are becoming more common in today’s technology, especially since screen fatigue is a concern.

We live in the era of service design and along with it, there are innumerable possibilities to create intuitive and human-centred experiences that so many people love.


So, how are designers and engineers addressing these challenges?


Voice Interface Interfaces (VUIs) are primary or additional visual, auditory and tactile interfaces that allow voice interaction between people and devices. Simply stated, a VUI can be anything from a flashing light when your voice is heard in a car console. VUI does not require a visual interface – it can be completely audible or tactile (eg vibration).

While there’s a vast spectrum of VUI, they all share a set of common UX fundamentals that drive usability.

Web services and the Internet of Things provide ready-made opportunities for voice (sensors, and readouts all make for natural smart home integrations).

The science for it is accessible, nowadays everyone can leverage what they’ve been learning in fields like Automatic Speech Recognition (ASR), Natural Language Understanding (NLU) and Text Speech (TTS).

Also let’s not forget the dawn-breaking AI, which is making VUIs, even more, smarter, thanks to it VUIs are learning and adapting to users’ speech, patterns, preferences and contexts.

All of these advances lead to an inflexion point in voice technology. But the basic driver is no technology; we are. We welcome voice experiences because we are connected through speech.

“A user’s voice command consists of three key factors: the intentutterance, and slot.”

The intent represents the broader objective of a user’s voice command, and this can either be a low utility or a high utility.

An utterance or How the User Phrases a Command reflects how the user phrases their request. For example, we know that the user wants to play music on the TV by saying “Play me… on the living room TV,” but this isn’t the only way that a user could make this request. For example, the user could also say, “I want to hear music ...on the living room TV”.

Designers as developers need to consider every variation of utterance. This will help the AI engine to recognize the request and link it to the right action or response.

Slots or the Required/ Optional Variables 

Sometimes a single intention is not good enough, and more information is needed from the user to meet the request. Alexa calls this “slot,” and slots are like traditional formal fields, meaning they may be optional or necessary, depending on what is required to complete the request.

In the above request, the slot is “relaxing” since the request can still be completed without it, this slot is optional. For booking a taxi for example a slot would be the destination and it would be required.

Optional overwrite any default values; for example, requesting to add to the calendar that you have to put a meeting next week with Jane Doe overwrites the default value of “as soon as possible”.


Do you want to build your own VUI?


  1. You have the technology and all the means necessary to do it; have you thought about the service or product you’re “designing” for?
  2. Have you mapped out the desired “conversation”?
  3. A user will typically search for the easiest way to complete a task, but their definition of “easy” may vary depending on context and situation.
  4. Examine your own experience and familiarity with voice and language interfaces.
  5. Talk to specific people you know who are more likely to be using this kind of interface also learn about the context in which they’ll likely be using it.
  6. You might want to create a sequence diagram that represents the pattern of interaction.
  7. Take into consideration the security risks it can introduce.
  8. Be clear about the timeline and topics when the interface isn’t the best option.
  9. Choose the idiosyncratic elements that fit your service and identify how they are expressed in the interface.
  10. Be aware of any existing prejudices and evaluate or adjust accordingly.
  11. Consider or the limitations and specific circumstances – such as accents, speech impediments and bilingual households – ensure a human-centred voice UI by designing to accommodate these particular needs.
  12. Keep the communication Simple and Conversational
  13. Confirm when a task has been completed
  14. Create a strong Error Strategy

Be the test user of the existing VUI devices and make a list of the things you like and dislike and make them better.

We don’t have so many limitations as we had let’s say 10 years ago, the world is your oyster!

Inspiration from: