Designer’s Guide to [VUI] Voice User Interface
UI Design

Designer’s Guide to [VUI] Voice User Interface

4 minutes read

Habil Emmanuail Sep 18 2019

Voice User Interface Design

The Future of Everything

We are moving towards a world with lesser physical interactions and more verbal interactions. Instead of typing out things and tapping for commands we can just speak them out. In recent times, millennials and gen Z were known to have more interactions with their smart devices instead of communicating face to face. Now these interactions are verbal with robots of smart devices.

In older science fiction, the future was one where humans became more robot like (bionic/ cyborg). But the current reality of the future is that we are teaching robots to be more human like. We have taught them to talk like humans and distinguish various speech patterns. They can perform tasks for us in a human fashion, like booking reservations at a restaurant.

This is where voice user interface (VUI) comes  in.  In its initial stages, it required a human to create personas and develop entire conversations. Humans were puppeteering everything. They were the ones distinguishing various human speech patterns and giving out responses, especially for the oddities and unexpected events. Experts are trying to create a system where the bot can develop a sense of self and recognize changes itself. Once the persona and initial framework has been set, the bot can evolve on its own without human help.Now it is a very believable future where bots will be handling almost everything for us.

However, some experts at Alexa think that older technology will still carry on. They still get to work on computers and use keyboards only for command prompt. That is something that might stay.

VUI- a Detailed Analysis

Google, Amazon and Apple are best known for their voice user interface technology with smart home devices which are purely voice based. There are no screens and no tapping or gestures are required unlike CUI (conversational user interface) where you also get a conversation on screen (SMS chat format) and you can tap for further details.

The top 5 tech companies of modern times have heavily invested in VUI technology. These include Google, Apple, Amazon, Facebook and Microsoft. Facebook still has a lot to catch up on compared to the other tech gurus.

Similar to a CUI, the UX designers start off by looking into what the target audience requires. They have to have a precise understanding of human conversations and the psyche. Journey mapping using voice is an excellent tool for this. User testing is another way to find out exactly  what the user wants out of the VUI experience.

UX design experts at Google believe that empathy is key when looking at user needs. You need to be aware of an international market and how each area has its own needs and the way they interact with technology is completely different. For example, people in Pakistan might be using technology differently than the people of Indonesia. Then the designer needs to be aware of the million ways that people phrase their sentences. These are known as utterance.

The UX design experts are constantly listening to and learning from human and bot conversations. Developers prepare a human like persona for bots. Examples of this are Siri, Google assistant and Alexa. All three of these have unique characters, personalities and voices.

The bot could be handling a low utility command like reading the news or setting up an alarm. Or it could be handling a high utility or specific command like turning on or turning off a switch anywhere in the house or set the thermostat to your desired temperature. You might want to give the bot a command and it will give you a follow up response. For example, what is today's news update? Or you might just want a general conversation. This might involve information about the bot. Like what is your favorite color?

At times the bot needs extra information from the user for specific commands like ordering an Uber. What is your destination? These are known as slots.

The developers write possible conversations and give appropriate voice to the persona of their bot. This might be for a hands free home device or for a smart screen app. The final product is a bot which can interact with humans in the most human like way. UX experts at Google say that giving bots a humanist persona is not to fool people and pretend like they are talking to an actual human, but to make a smoother conversation. The more robot like voice, the more people will hesitate to interact with the bot. With a humanistic approach, people will be more comfortable interacting with the bot.

Endless Possibilities

Google and Amazon both have provided kits in the form of Google Home Action and Alexa Skills for developers to add voice to their own apps.There are endless possibilities presented by both tech giants as to what voice can achieve. Apple will soon be following with Siri kit to join the competition. Alexa skills can be created to order an Uber, shop online, pay bills and etcetera. Similarly Google Assistant can help you with day to day tasks. You can control utilities and switches around the house, play music, order an Uber and so much more.

A Final Standpoint

There is a lot more detail involved when developing VUI. These are just the basics of what VUI is and how drastically it is going to affect our lives in the not so distant future. As an end user, we are bound to see fascinating new technology in the future in terms of VUI.

Habil Emmanuail

Habil Emmanuail

Habil is an IBM certified Design Thinking practitioner and a member of the Interaction Design Foundation. He has been working as a UX consultant and User Centered designer across web and mobile applications for almost four years. His area of expertise include UI/UX Design, UX Research, Visual UI Design, Prototyping, Information Architecture, Agile Scrum, Branding as well as HTML/CSS, UX Writing, Research and Analytics and Strategy and Planning.