VUX World

Today, we’re getting into detail about what it’s like to be a full-time VUI designer. We’re discussing the details of the role, the day to day duties and the skillsets that are important to succeed in designing voice user interfaces.The role of a VUI designer has been around for a while, but it’s not so common. However, with the rise of voice as an access point for controlling technology, this is one of the roles of the future.If you’re planning for that future and are considering seeking work in the voice first space; or if you’re a voice first design hobbyist looking to take it full-time; or if you’re generally interested in what it takes to create conversational interfaces, then this is a great episode for you.We’re joined by two professional VUI designers, Ilana Shalowitz and Brian Bauman of Emmi, and together they’ll be taking us through the ins and outs of the role that designs voice user interfaces for Emmi’s care calls.In this episodeIlana takes us through an overview of the VUI designer role and discusses what skillsets are important. She takes us through the interview process, bedding in, and drops some detailed knowledge voice user interface design based on her years of experience in the field.Brian then takes us through the role in more detail and looks at the specifics of the role, where a VUI designer fits into a project, what the day to day activities and duties are, and what he found during his first 30 days.We also discuss things like:How to pronounce VUI (V.U.I. or "Vooey")The difference between chat bot design and conversational vuiWhat is prosity and why is it importantLanguageBreathingError recoveryDirecting voice talentReporting and measuring successBroader voice user interface design tipsOur guestsIlana Shalowitz is the VUI Design Manager at Emmi and has a background in marketing and design. Ilana is forming a great reputation in the voice first space and is quickly becoming a leading voice for voice in the healthcare sector. She featured at the Alexa Conference 2018, spoke at the AI Summit 2018, has featured on the VoiceFirst.FM Voice of Healthcare podcast (Episode 5) and is a keynotes speaker at the Voice of Healthcare Summit in August in Boston.Brian Bauman is a former playwright and joined Emmi recently, taking on his first role as a VUI designer. Brian has a background in the creative arts and is a former playwright. He fills us in on what his first month as a VUI designer was like and how his creative background gave him some valuable transferable skills.About EmmiEmmi solutions is part of the Wolters Kluwer stable and helps care organisations extend the reach of their care through using technology.Ilana and Brian both wore on the automated voice-based outbound calls side of the company. They create call scripts and dialogue flows that are turned into real calls that patients receive and can interact with in conversation. This means that healthcare providers can speak to thousands of patients without needing make make any manual calls at all.LinksApply to be a VUI designer at EmmiJoin the VUI designer slack channelFind out more about EmmiRegister at the Voice of Healthcare Summit 2018 Hosted on Acast. See acast.com/privacy for more information.

We’re talking to ex-Googlers, Konstantin Samoylov and Adam Banks, about their findings from conducting research on voice assistants at Google and their approach to building world-leading UX labs.This episode is a whirlwind of insights, practical advice and engaging anecdotes that cover the width and breadth of user research and user behaviour in the voice first and voice assistant space. It’s littered with examples of user behaviour found when researching voice at Google and peppered with guidance on how to create world-class user research spaces.Some of the things we discuss include:Findings from countless voice assistant studies at GoogleReal user behaviour in the on-boarding processUser trust of voice assistantsWhat people expect from voice assistantsUser mental models when using voice assistantsThe difference between replicating your app and designing for voiceThe difference between a voice assistant and a voice interfaceThe difference between user expectations and realityHow voice assistant responses can shape people’s expectations of the full functionality of the thingWhat makes a good UX labHow to design a user research spaceHow voice will disrupt and challenge organisational structureIs there a place for advertising on voice assistants?Mistakes people make when seeking a voice presence (Hint: starting with ‘let’s create an Alexa Skill’ rather than ‘how willpeople interact with our brand via voice?’)The importance (or lack of) of speed in voice user interfaces?How to fit voice user research into a design sprintPlus, for those of you watching on YouTube, we have a tour of the UX Lab in a Box!Our GuestsKonstantin Samoylov and Adam Banks are world-leading user researchers and research lab creators, and founders of user research consultancy firm, UX Study.The duo left Google in 2016 after pioneering studies in virtual assistants and voice, as well as designing and creating over 50 user research labs across the globe, and managing the entirety of Google’s global user research spaces.While working as researchers and lab builders at Google, and showing companies their research spaces, plenty of companies used to ask Konstantin and Adam whether they can recommend a company to build them a similar lab. Upon realising that company doesn’t exist, they set about creating it!UX Study designs and builds research and design spaces for companies, provides research consultancy services and training, as well as hires and sells its signature product, UX Lab in a Box.UX Lab in a BoxThe Lab in a Box, http://ux-study.com/products/lab-in-a-box/ is an audio and video recording, mixing and broadcasting unit designed specifically to help user researchers conduct reliable, consistent and speedy studies.It converts any space into a user research lab in minutes and helps researchers focus on the most important aspect of their role - research!It was born after the duo, in true researcher style, conducted user research on user researchers and found that 30% of a researchers time is spent fiddling with cables, setting up studies, editing video and generally faffing around doing things that aren’t research!Konstantin SamoylovKonstantin Samoylov is an award-winning user researcher. He has nearly 20 years’ experience in the field and has conducted over 1000 user research studies.He was part of the team that pioneered voice at Google and was the first researcher to focus on voice dialogues and actions. By the time he left, just 2 years ago, most of the studies into user behaviour on voice assistants at Google were conducted by him.Adam BanksIt’s likely that Adam Banks has more experience in creating user research spaces than anyone else on the planet. He designed, built and managed all of Google’s user research labs globally including the newly-opened ‘Userplex’ in San Francisco.He’s created over 50 research and design spaces across the globe for Google, and also has vast experience in conducting user research himself.LinksVisit the UX Study website Follow UX Study on Twitter Check out the UX Lab in a Box Follow Kostantin on Twitter Follow Adam on Twitter Hosted on Acast. See acast.com/privacy for more information.

This week, Dustin and I are joined by Matt Hartman, partner at Betaworks, curator of the Hearing Voices newsletter and creator of the Wiffy Alexa Skill.In this episode, we’re discussing:All about BetaworksA strategic vision for voiceChanging user behaviourOn-demand interfacesFriction and psychological frictionHow context influences your design interfaceThe 2 types of companies that’ll get built on voice platformsDifferences between GUI and VUI designVoice campThe Wiffy Alexa SkillLessons learned building your first Alexa SkillText message on-boardingChallenges in the voice spaceOur Guest, Matt HartmanMatt Hartman has been with Betaworks for the past 4 years and handles the investment side of the company. Matt spends his days with his ear to the ground, meeting company founders and entrepreneurs, searching for the next big investment opportunities.Paying attention to trends in user behaviour and searching for the next new wave of technology that will change the way people communicate has led Matt and Betaworks to focus on the voice space.Matt has developed immense knowledge and passion for voice and is a true visionary. He totally gets the current state of play in the voice space and is a true design thinker. He has an entirely different and unique perspective on the voice scene: the voice ecosystem, voice strategy, user behaviour trends, challenges and the future of the industry.Matt curates the Hearing Voices newsletter to share his reading with the rest of the voice space and created the Wiffy Alexa Skill, which lets you ask Alexa for the Wifi password. It’s one of the few Skills that receives the fabled Alexa Developer Reward.BetaworksBetaworks is a startup platform that builds products like bit.ly, Chartbeat and GIPHY. It invests in companies like Tumblr, Kickstarter and Medium and has recently turned its attention to audio and voice platforms such as Anchor, Breaker and Gimlet.As part of voice camp in 2017, Betaworks invested in a host of voice-first companies including Jovo, who featured on episode 5 of the VUX World podcast, as well as Spoken Layer, Shine and John Done, which conversational AI guru, Jeff Smith (episode 4), was involved in.LinksSubscribe to the Hearing Voices newsletterCheck out the Wiffy Alexa SkillFollow Matt on TwitterVisit Matt's websiteMatt's article: Interfaces on demandMatt's article: Lessons Learned Building my First Alexa SkillFollow Matt Hartman on MediumFind out more about Betaworks Hosted on Acast. See acast.com/privacy for more information.

This week, we’re joined by the Mycroft AI team, and we’re getting deep into designing and developing on the open source alternative to Amazon Alexa and Google Assistant.If you’ve tried creating voice apps on platforms such as Amazon Alexa and Google Assistant, then you’ll do doubt be familiar with their current limitations. Push notifications, monetisation and all-round flexibility generally leave plenty to be desired.What if there was an alternative? A platform that really did let you create whatever you wanted. Something that'll let you monetise. Something completely open to being used in a way that you want to use it.Well, that’s what the team at Mycroft AI have built.What is Mycroft AI?Mycroft AI is the world’s first open source voice assistant that runs anywhere. On desktop, mobile, smart speakers. In cars, fridges, and washing machines. You name it. You can put it where you like and do with it what you like as well.One member of the Mycroft community has hooked the platform up to a webcam and created a facial recognition feature that uses a persons face instead of a wake word. When you look at the camera, the speaker wakes and is ready for you to speak to it!As well as being open source and flexible, if you create something exceptional, then it could even become the default skill for that feature on the platform. That’s like you creating a really great weather skill on Alexa and Amazon using that as the default way to tell people the weather!Plus, your personal data is kept totally private.And Mycroft aren’t just creating cool software, they have a range of smart speakers as well. The Mark I speaker is on sale now and the Mark II is on Indiegogo right now.Our GuestsToday, we’re joined by Joshua Montgomery, CEO; Steve Penrod, CTO; and Derick Schweppe, CDO to talk all things Mycroft AI.We’re also joined again by co-host, Dustin Coates, and we’re getting into detail about:Where Mycroft AI came from and the company’s vision for voice and AIThe differences between Mycroft and the other players such as Alexa and Google AssistantThe value of an open source voice assistantAbout the platform (how it works, how you can get up and running)About the range of smart speakersPrivacy and securityThe Mycroft community and what people are buildingIncentives and reasons to develop on Mycroft AIDev Chops with Dustin: a new feature where Dustin gets into the dev details of the Mycroft platformVoice design techniques and processesThe future of voiceLinksVisit the Mycroft websiteGet Mycroft for developersMycroft Mark II on IndigogoBuy Mycroft Mark 1Mycroft on YoutubeMycroft on TwitterMycroft community forumMycroft chat Hosted on Acast. See acast.com/privacy for more information.

But first, let's welcome co-host; Dustin CoatesWe're joined in this episode by our new co-host, Dustin Coates. Dustin is the author of Voice Applications for Alexa and Google Assistant and has been involved in the voice scene since day 1. With extensive experience in software engineering, deep knowledge of Alexa and Google Assistant development and an immense passion for voice, Dustin brings a new perspective and different angles of questioning that, not only technical folk, but non-tech people will appreciate as well.One of the challenges with new technology platforms is that you typically need to be able to speak the lingo to develop on them. As the internet has progressed, there are what seems like a million dev languages that you'd need to be able to code in to be able to create your website or app.It wasn’t until relatively recently that tools cropped up to allow designers and total beginners to build on the web. Tools like Wordpress, Weebly and Squarespace have made it easy for anyone to create a presence online.The great thing about having that history of the web is that we can learn from the past and apply the things that work well to new industries and technology. That’s exactly what Vasili has done through the creation of Storyline. It's the Weebly of voice.It has a drag and drop interface and a user friendly workflow that will allow anyone to create an Alexa Skill without needing to code a single line.It will let more technical folk do further work if they’d like to, such as using an API integration to interrogate data, but for the less technical folk out there, what you get ‘out the box’ is more than enough to build a well-rounded Skill.In fact, testament to how much flexibility is baked into the tool is the recent announcement of the Amazon Alexa Skills Challenge: Kids winner, Kids Court, was created in Storyline.In this episode, we get into detail about:What Storyline is, how it works and how to get up and runningTesting and publishing SkillsHow to make your Skill more discoverableThe Storyline communityFuture features and the roadmapThe challenges facing developers and solutions to solving themVasili’s vision for where the voice space is headingAdvice for beginner Skill-builders and voice headsOur guestVasili Shynkarenka is the founder and CEO of Storyline. After creating and selling an agency that specialised in creating conversational experiences for brands, Vasili turned his attention to focus on Storyline.Vasili is madly passionate about voice and has immense experience in the field. He’s super-keen for all kinds of people to get involved in creating voice experiences, no matter what their skill level. His vision for the future of smart speakers and his knowledge of creating voice experiences are inspirational.This episode is packed with insights and tips and tricks to help people of all skill levels create an Alexa Skill.LinksTry Storyline Check out Storyline on YoutubeJoin the Storyline community on Facebook Read Vasili's article 'What I Learned from 5000 Reviews of Top 5 Alexa Skills' on MediumCheck out Vasili on Medium Hosted on Acast. See acast.com/privacy for more information.

Find out all about the Jovo framework that lets you create Alexa Skills and Google Assistant apps at the same time, using the same code!You know how you always need to write platform-specific code for everything? One lot of code for your iOS app, another load for Android and more for Windows (if you even bother). Well, the same challenges exist today when creating voice apps. Well, those challenges did exist, until Jovo came along.With the Jovo framework, you can create an Alexa Skill and a Google Assistant app all from the same lot of code. It's part of Jovo's bigger mission to enable you to create multi-modal experiences with ease and to join together the sporadic tech outlets to create a unified experience across all devices and platforms.Our GuestJan König is one of the co-founders of Jovo and we're speaking to him today about all things cross-platform voice development. We'll hear from Jan about things like:what 'multi-modal' actually meansfeatures of the Jovo frameworkthe Jovo community and Jovo Studiosthe differences between developing for Alexa and Google Assistantthe challenges of developing voice experiencesthe skills needed for building Skillsdesigner and developer relationships in the voice worldtesting voice appsJovo 1.0 and the future of Jovo andLinksFollow Jan on TwitterFollow Jovo on TwitterVisit the Jovo websiteJovo on GithubJovo Slack channelFollow Jan on Medium Hosted on Acast. See acast.com/privacy for more information.

Conversational AI crops up constantly in conversations about voice, but what actually is it? How the heck does it work? And how can you use it? We speak to Jeff Smith to find out.In this episode, we cover:An overview of conversational AI - what it is and how it worksThe role of voice in conversational AIHow and why brands should consider using itHow you can get started with machine learning and conversational AIChallenges and opportunities such as the state of analytics and securityAt the foot of the show, I said that this was:“One of the most interesting conversations I’ve ever had in my life.”And I wasn’t lying.Getting to grips with Conversational AIIf you’re not familiar with the concepts of conversational AI, this episode will give you a great introduction.If you are familiar and work in the industry, Jeff drops some great nuggets and learnings from his extensive experience.And if you’re interested in this from a branding perspective, by the end of this episode, you’ll have a full understanding of the contexts and environments where it’s useful.Our GuestJeff Smith, author of Reactive Machine Learning Systems, has bags of experience in the area of machine learning and conversational AI. He’s built a series of AIs, including Amy and Andrew at X.ai (what a cool domain!). That’s an AI Personal Assistant that helps people schedule meetings.Jeff now works with IPsoft and manages the conversational AI team who’re building Amelia. Amelia, as you’ll find out in the show, is an extremely sophisticated AI that can perform many human tasks, increasing productivity and business efficiencies.LinksJeff's book, Reactive Machine Learning SystemsJeff's talks and content on Reactive Machine LearningFollow Jeff on TwitterIPsoft website where you can check out AmeliaFollow IPsoft on TwitterJeff's article, 'Better conversations with machines'Check out Jeff on MediumHear Donald Trump on Lyrebird Hosted on Acast. See acast.com/privacy for more information.

In this episode, we’re going to show you how you can build an Alexa Skill from right within Wordpress.Wordpress powers almost a third of the internet and now millions of websites running Wordpress can all have a presence on voice. It’s all thanks to VoiceWP, the Wordpress plugin that lets you build an Alexa Skill from within the most widely adopted CMS on the planet.You can create Flash Briefings with ease and even have Alexa read the content of your website. We all know about audio books, but this could be the first opportunity to have your website content turned into audio form and read aloud as soon as its published, without you having to go through much effort at all. It’s super simple to set up.Our GuestVoiceWP was built by our guest, Tom Harrigan, Partner and VP of Strategic Technology at Alley Interactive, a full service digital agency that specialises in helping publishers succeed online. We speak to Tom about VoiceWP, which is allowing brands such as People.com and Dow Jones’ Moneyish.com build Alexa Skills and establish a presence on voice with ease.And you can use it too, because it’s free and super-simple to set up.So, if you use Wordpress as your CMS and you’re interested in testing the waters in voice, or if you’re looking for a starting point Alexa Skill building, then this episode is for you.We’re speaking to Tom about:Where the idea for VoiceWP came from and how it was builtWhat is the plugin all about and what features does it haveWho’s using it right now and who is it targeted atHow can you get up and running with the plugin and try it out for yourselfWhat does the future look like and what’s coming upLinksCheck out VoiceWPDownload VoiceWP at Git HubFollow Tom on TwitterVisit Tom's websiteFind out more about Alley Interactive Hosted on Acast. See acast.com/privacy for more information.

In this episode, we're talking about voice first user testing, why it's so imperative and how you can get started doing your own voice user testing.Why voice first user testing?Although usability testing graphical user interfaces is as common as a trending tweet, it's a seed that’s yet to be greatly sewn in the world of voice. There are many services that will provide technical testing, but those specifically offering voice first user testing in person with real users are few and far between. Enter, Userfy.Whether you create Alexa Skills, Google Actions or any other voice user experience, this episode will help you make sure that your voice user interface (VUI) works for the people that use it through teaching you how to approach a voice-based user testing project.We’ll cover things like:The current state of user research in the voice industryWhy is usability testing important?What kind of users should you test with?User testing processes and planningHow to approach a voice-first testing projectValidating assumptionsThe difference between graphical and voice user testingWhat tools and equipment you needIntroducing Sam HowardOur guest is Sam Howard, co-founder and Director of user research agency, Userfy, which specialises in user testing. Sam has a PhD in Human-Computer Interaction and a degree in Psychology. That, mixed with a love of technology and a passion for helping people, puts Sam at the forefront of the user research field.Links:Sam Howard on TwitterUserfy websiteUserfy on TwitterSam's 'Usability challenges facing voice-first devices' article Hosted on Acast. See acast.com/privacy for more information.

Ladies and gentlemen, boys and girls, welcome to VUX World.This introductory episode is all about what VUX World is all about. Here, I'll take you through:the aims of the showhow we intend to meet those aimswhy it existswho would find it usefulwhat's in store over the coming monthsThe aims of VUX WorldThis is an ambitious show that intends to cover three core aims for three primary groups of people:To help VUX pros create better voice experiences through bringing together people from throughout the industry to share insights, tools, tips and tricksTo help brands create voice first strategies and implement voice first solutions through learning from companies and agencies who're doing it right nowTo help grow the VUX industry by introducing people such as creatives, scientists, technologists, strategists, linguistics, developers and anyone else to the voice first worldHow we'll meet our aimsWe'll reach those aims through focusing on three core pillars of content.Why? We'll cover the 'why' aspect of the argument for voice. Why should you take this area seriously? Why develop your skills here? Why voice?How? We'll extensively cover the 'how' side of things, too. How can you get started? How does the voice industry work? How can you develop here? We'll cover things like tutorials, guides, tips, hints and tactics to help you learn, develop and grow to create epic voice experiences.What's stopping you? Every industry has its challenges. We want to delve into those challenges and uncover opportunities to push past the barriers and find opportunities to move forward.The host of VUX WorldYour host for this journey is me, Kane Simms. I have a history in sound design and music production as well as extensive experience in marketing, UX and agile project management. My love for all things audio and passion for understanding user behaviour and technology culminate perfectly right here in the world of voice.So, strap in, hold tight and brace yourself for the rapidly expanding world of voice. I'm glad to be your guide.Now, without further ado, you should totally check out the first proper episode of the podcast: User testing on voice-first devices with Sam Howard.Enjoy :) Hosted on Acast. See acast.com/privacy for more information.