At Voxable, we design and develop conversational user interfaces. We build everything from voice user interfaces, like Alexa Skills and Actions on Google, to custom chatbots. In our workshops, talks, and discussions with clients, we find it helpful to break down the conversational interaction loop — the way humans and machines communicate. It’s essential for anyone working with this technology to understand how machines handle conversation. For a human to converse with a machine at the most basic level, the machine must:

• Listen
• Understand
• Process
• Respond

I’m going to explore the core technology behind how machines accomplish these tasks and how that technology differs depending on whether it’s a voice or text conversation.

Listen

When a human speaks to a machine, the machine needs to understand the collection of sounds coming from the human’s voice and translate them into text. This is typically handled by machine learning algorithms trained to recognize human language from streaming audio — the technology is called automatic speech recognition (ASR). ASR is the process by which a computer recognizes the words a user is saying and converts them into text in real time.

Google Search by voice is a great way to visualize ASR in action.

ASR technology is built into browsers, operating systems, phones, and voice-first devices like Amazon Echo and Google Home. ASR accuracy has improved exponentially over the past few years with the introduction of new machine learning techniques, like deep learning, that make the technology much more reliable and usable on a broad scale. The interaction loop stops without ASR, so ASR accuracy is necessary to have highly-functional voice interfaces.

Nevertheless, ASR still faces challenges depending on the job it’s being asked to do and the context in which it’s being used. The wide range of voices, dialects, and accents interacting with ASR demand more from the technology. Rapid speech and background noise also pose a challenge. It’s necessary for conversational designers to understand how ASR affects their users specifically.

As you might guess, the process is somewhat simpler when a human is conversing with a machine via text because there is no translation from audio to text. Graphical user interfaces, like messaging apps, have a variety of different design affordances that improve interactions. Menus, image cards, and quick reply buttons are just some of the tools conversational designers can leverage to facilitate conversation.

Facebook Messenger provides several types of structured messages like suggested replies, card galleries, and rich media.

Understand

Whether the text originates from a human speaking or typing, language is messy and machines have a hard time understanding it. Machines must be taught to take human language and translate it into structured data automatically. Enter natural language understanding (NLU). NLU is the technology that translates messy human language into structured data. In a conversational interface, the data that is extracted from NLU includes the information or entities that are important to accomplishing a user’s goal.

The rise of accessible and affordable NLU platforms like Google’s Dialogflow, IBM Watson, and Microsoft LUIS has fueled innovation in the conversational interface industry. Startups and independent developers can utilize these platforms and no longer need to invest in a team of data scientists and PhDs to build custom statistical models of human language.

Technology companies invest massive amounts of time and money to advance machine learning and increase machines’ ability to understand humans. As a result, machines are learning to understand human elements of communication like the context of a conversation and the emotional state of users.

Process

Once meaning and data are extracted from the text, a system or logic must be put in place for how the machine handles that information — this is called bot intelligence. Bot intelligence takes data extracted from the NLU and combines it with contextual data and business logic to handle the complexity of conversation. For example, a chatbot may need to ask follow-up questions to clarify the user’s intent in order to perform the correct action.

In a conversational interface, bot intelligence manages the:

• User’s State — The user’s tools, setting, emotional state, expectations (qualities uncovered during research)
• Conversational State — Where the user is in the conversation thread, what’s already been discussed, and specifics a user might reference
• Application State — All of the data retrieved from other systems via application programming interface (API) calls that will be used to execute actions on behalf of the user.

Bot intelligence encompasses the logic a machine requires to have in-depth conversations with humans and accomplish their goals.

Respond

After performing an action and retrieving information, the machine must generate a response that is valuable to the human. The response could communicate the state of an action, relay information, or request more information from the user.

Voice-based interactions use audio feedback, synthesized speech, and recorded audio to deliver responses. Using synthesized voice is the most cost-effective method for a voice interface to deliver responses. Synthesized voice, also known as text-to-speech (TTS), is technology able to mimic a human voice by translating written language into sounds that humans recognize as speech. This technology now generates better and more human-like voice quality, so much so that it’s even able to mimic real celebrity and politician voices.

Recorded audio options, such as voice-overs and sound effects, are also important elements in a voice interface and, when used well, further reinforce the brand and improve communication.

For text-based interactions, the response is delivered through a graphical user interface like a messaging app. The various affordances of each messaging app — such as menus, image cards, and quick reply buttons — help deliver rich information and structured content.

—

Hopefully, this breakdown of the way conversational user interfaces work demystifies how humans and machines communicate. Successful interaction between a human and computer is similar to successful interaction between two humans: it involves listening, understanding, processing, and responding appropriately. Building a shared understanding of the users’ needs and helping them achieve their goals is a lofty task, but it’s core to the work of successful conversational design.

Written by Brittany Walla, Marketing Director at Voxable. Originally published at www.voxable.io on May 9, 2018.

The Conversational Interaction Loop was originally published in Austin Startups on Medium, where people are continuing the conversation by highlighting and responding to this story.

I’m a big fan of A Book Apart. I’ve been reading their brief books on design, writing, and code since I bought a 3-pack of their first titles in 2012. Throughout the years, I’ve picked up many A Book Apart books, and they have all been incredibly insightful and useful. Their most recent title, Erika Hall’s Conversational Design, is no exception.

I was lucky enough to attend Hall’s talk “Design with Words” at the 2016 Talkabot conference where she introduced many of the ideas she explores in the book. That talk and Conversational Design wonderfully encapsulate the opportunity a conversational design framework offers interface designers. She covers many of the concepts I discuss regularly with other conversational designers. Additionally, Hall lends fresh, new perspectives about how to further refine one’s process and approach conversational design.

Conversational Design illuminates how conversational design can influence the strategy, research, and design of every type of interface we build. Hall weaves in history, philosophy, and psychology to reveal how conversation is the basis for interaction and an effective design framework.

“Conversational design is truly human-centered design, every step of the way. There is no next big thing, only the next step in an unfolding story of how people use technology to be themselves.”

As Hall examines the ways humans converse, such as texting and verbal conversation, she describes the notion of orality — the human tendency to share concepts through language. Hall recounts our social history as an oral culture, before literacy and writing made us more individualistic. I find these historical points especially interesting as a designer in the midst of a technological revolution that upends our previous notions of orality and literacy.

“Now we can start imagining, in an open-ended way, what constellation of connected devices any given person will have around them, and how we can deliver a meaningful, memorable experience on any one of them.”

The conversational design approach suits this new technological landscape well because it centers around how humans have always exchanged information and ideas — via conversation. Conversational design melds the practice of human conversation with current technological advancements like social media and artificial intelligence. Conversational exchanges comprise a large part of internet culture and support the ideals of a more connected, decentralized society.

Conversational Design also delves into the collaborative principles of conversation — Grice’s Maxims and how those principles translate to interface design.

“The essential point is this: use the principles of what makes everyday human interactions productive and satisfying to inform computer-mediated interactions.”

Hall helps designers understand how to apply those principles in practice. She outlines how we can handle the most important moments in interaction: introduction, orientation, action, and guidance then stresses the importance of personality as a unifier of all these principles. I’m especially interested in incorporating the personality development and branding exercises she describes into my own branding process.

Hall does not shy away from pointing out some of the shortcomings of design and the tech industry as a whole. She lays out concepts that drive better design processes, such as collaboration amongst teams as well as with users. Teams should collaborate through meaningful conversations rather than organization divisions and hierarchy. In kind, those teams should have conversations with users through research, prototyping, and testing. She provides clear, actionable tips for designers to implement those processes in their organization.

“Creating a design process is just another type of interaction design. A group of people sharing a system need to behave a certain way and have access the right information at the right time to get a successful outcome.”

Above all, Conversational Design is a thought-provoking read for any designer who is interested in learning how to research, write, and design an interface better. I will keep this book at my desk to refer back to the slew of highlights, notes, and exercises it contains.

Written by Lauren Golembiewski, CEO and Co-founder of Voxable. Originally published at www.voxable.io on April 17, 2018.

The introduction of new technology into a business’s strategic plan is a simultaneously exciting and daunting idea for many stakeholders. The newer the tech, the more uncertain the ROI is and the more unwilling risk-averse decision makers might be to implementing it. However, there is some truth to the notion that with great risk comes great reward. Few businesses have successfully capitalized on the opportunities chatbots and voice interfaces afford, so being one of the first to do so in any given industry has the potential to produce monumental returns.

Since taking the position as Voxable’s Marketing Director and immersing myself in the tech world, I’ve found the majority of business owners and stakeholders we market our services to have a superficial knowledge of conversational technology. Most have heard about chatbots, Alexa Skills, Actions on Google, etc., but they aren’t entirely sure how this technology applies to their business and the ways it could positively affect their bottom line. The knowledge gap is understandable as there is typically a lack of documentation, case studies, and reliable resources in new, innovative fields. This is why Voxable values writing and speaking about conversational interface design and development. It is also my inspiration for this post. Here are the five most effective ways businesses can utilize chatbots and voice interfaces:

1. 📊 Conversational Marketing

Conversational marketing is a new strategy that leverages the popularity and immediacy of messaging channels. It enables brands to engage with an audience through one-on-one conversational interactions. Marketers can deliver content and send notifications automatically through popular messaging channels such as Facebook Messenger to build their brand and move consumers down the sales funnel.

As more people adopt messaging as their preferred method of communication, brands must shift marketing tactics to reach their audience. I make a case for conversational marketing in a previous blog post; it’s on track to replace, or at the very least supplement, most brands’ email marketing strategy in the near future.

Voice-first devices, such as Amazon Alexa or Google Home, offer other relatively unexplored opportunities for conversational marketing. Consumers’ rapid adoption of this technology has created a unique and uncrowded space for brands to enter. Brands like Tide and Johnnie Walker are already taking advantage of the devices’ hands-free, ubiquitous nature. Voice search is also on the rise. Marketers must consider voice SEO and how it might impact a website’s overall ranking. Using structured data, improving featured snippet text, and altering or creating content to connect with users’ queries should all be on marketers’ website voice search optimization list.

2. 💰 Conversational Commerce

Conversational commerce is how businesses sell products and services as well as transact through messaging platforms. Conversational interfaces enable companies of all sizes to offer automated, concierge-like experiences for consumers as they shop online.

Consumers are more likely to make purchases from businesses that offer live-chat assistance. However, staffing a human support team 24/7 is very costly for businesses. Companies can use conversational interfaces to automate conversations that assist consumers in making purchase decisions and convert them to customers — interactions that were previously unsustainable to support for most businesses.

Now that conversational interfaces have integrated payment into platforms so consumers can pay for something at the click of the button or via voice command, it won’t be long until the majority of people prefer the convenience of conversational commerce over other shopping methods. By looking at the success of retailers like Amazon and Apple in the digital marketplace, it’s clear the businesses that offer consumers easy, intuitive purchasing options will increase their market share and revenue exponentially.

3. 🙋‍ Conversational Support

Conversational support is the automated way businesses assist customers or users via a messaging platform. Similar to conversational commerce, conversational support enables any company to offer practical guidance and help around the clock.

People frequently pose the same questions to a business’s support professionals. Conversational support interfaces allow those people seeking help to interact with a company in a conversational manner and find the answers they need, whenever they need them, without human interaction. This satisfies situations in which searching for answers on a company’s website is too cumbersome and frees up support staff for more complicated queries.

According to the 2017 Aspect Consumer Experience Index, 59% of consumers prefer customer service options like chatbots that do not involve talking. The key takeaway for any business owner with large support staff is that implementing a conversational support solution cannot only significantly decrease company overhead, but also better satisfy customers.

4. 📱 Conversational Consumer Apps

Conversational consumer applications are a way for businesses to make complex web interfaces easier to understand and use via natural language. When people approach an app, they have an idea of what they need to do — an intent. Conversational apps take on more work to help users find what they need and accomplish their intent using natural language instead of relying on them to navigate through a highly visual interface.

The market indicates consumers are experiencing application fatigue; they are downloading and engaging with fewer apps than ever. Therefore, it is vital for businesses to make their app as easy and delightful to use as possible.

With 1.3 billion Facebook Messenger users and over 33 million voice-first devices in homes around the world, it is necessary for companies to determine how to embrace the conversational trend. Businesses can integrate their existing apps with conversational apps that users already have installed like Facebook Messenger, add conversational interfaces to their existing apps, or create brand new conversational apps to satisfy users.

5. 💻 Conversational Enterprise Apps

Conversational enterprise applications integrate within companies’ chat applications such as Slack, HipChat, and Microsoft Teams. These interfaces help organizations increase productivity and enhance communication between employees, external teams, clients, and vendors by automating repetitive tasks and information delivery.

People are beginning to spend more time conducting work within chat apps than via email. The widespread use of this technology means there is a huge opportunity to help people better communicate through these channels. Streamlining a business’s internal communication can increase employee efficiency and promote effective collaboration. For workplaces that use chat apps regularly, investing in a conversational enterprise app might have a greater return than investing in one that’s consumer-facing.

–

Conversational interfaces have the potential to affect almost every aspect of business and understanding their many uses is the first step to building a comprehensive conversational strategy.

Written by Brittany Walla, Marketing Director at Voxable. Originally published at www.voxable.io on April 12, 2018.

5 Business Use Cases for Conversational Interfaces was originally published in Austin Startups on Medium, where people are continuing the conversation by highlighting and responding to this story.

This post is part three of a three-part series on branding bots. Read part one on voice and tone and part two on brand personas. In this final edition, we’re going to bring it all together and talk about applying these concepts to designing a conversational user interface (CUI).

Understanding users makes your CUI better at talking with them.

Developing a brand relies on having an understanding of your audience’s values, needs, and desires. Conversational interfaces foster a more intimate interaction with users that our typical screen-based interfaces. Because of this intimate relationship, they require a deep understanding of users’ expectations. There are numerous ways to uncover insights about users that will guide branding, but I’m going to cover a couple Voxable’s favorite methods.

Our go-to research method for better understanding users is to talk with them in the environment where they would be interacting with the interface. Through user interviews, we focus on understanding the Jobs-to-be-Done as well as gather insights about users’ values, concerns, and the language they use. Pairing user interviews with a competitive brand analysis lays the foundation for the brand direction.

Brand affects nearly every part of a business and evolves as the business matures. We focus on brand throughout the entire design process, not just at the beginning. We usually incorporate branding questions while testing prototypes as well as in interviews with subjects participating in a Wizard-of-Oz usability test. These are both incredibly valuable methods for observing the interactions users have with a conversational interface — how they perceive and understand the language the interface uses.

Document a voice and tone style guide.

Branding and design decisions should be maintained in living document that can be shared and collaborated upon across teams. The exact format of a voice and tone guide is not particularly important, other than it should be something that works for your business and team needs. At Voxable, we often use Google Docs or Atlassian Confluence because they are easily accessible, have inline commenting, and can be iterated upon long after we complete our project. Here are some of the things we typically outline in a document:

• Qualities of the Brand Voice Describes the characteristics of the brand and conversational voice. We work with stakeholders and users to determine these qualities. Is the brand young and hip? Authoritative? Sarcastic?
• Key Terms Defines how terms should be used consistently in the language.
• Emoji Dictates which concepts core to our brand we using emoji to express.
• Grammar and Usage Establishes how to use punctuation, capitalization, and symbols like the ampersand in textual interfaces.
• Tone Outlines key moments tone shifts; includes several examples and variations for responses. Voice should be very consistent across a brand, but the tone shifts depending on the situation. Here are some examples of those moments:
• Greeting
• Introduction
• Re-prompts
• Errors
• Success
• Help
• Small Talk
• Tutorials

Knowing the moments to define is all about understanding your users’ experiences and how language affects them in the interface. The guide becomes indispensable the more a CUI is iterated upon and it helps teams more effectively collaborate to keep the experience consistent.

Documentation of emoji use in a chatbot style guide.

Invest in creating a persona or character.

Building characters is fun and challenging, and they can be an effective way to express your brand in a conversation. Characters help create a story and build empathy with users.

The user journeys Voxable establishes in the research phase serve as a sort of plot device for the character. Thinking about how your character responds and evolves as users interact with it creates a more impactful story.

Every brand will have a different level of investment in creating a character, but I’m going to outline the way we define a character. To establish our characters, we create character profiles that describe the character’s qualities, history, and motivation:

• Avatar
• Archetype
• Name
• Origin Story
• Super Powers
• Flaws (this might weave into the conversation how the character is automated and prone to mistakes)
• Lingo
• Gender
• Values

Some of these characteristics may not make sense for every brand, so we incorporate different ones depending on the direction. Check out the Dungeons and Dragons character template for inspiration for describing characters.

As I’m establishing the qualities of a character, I also pull inspiration for illustration direction on sites like Dribbble, Designspiration, Motionographer, and Pixar; this helps me provide direction to an animator or illustrator. Great animators and illustrators are fantastic resources when building a brand character. They are trained in visualizing stories and bringing characters to life.

Example sketch of a character profile.

Refine the interface elements.

Once I’ve established voice, tone, and (possibly) persona, I extend the defined brand to the aural and/or visual elements of the interface.

Audio signatures, also called earcons, are tones or audio clips that are designed to represent a brand. Think of NBC’s chimes or HBO’s TV static. These signatures ground users in a brand and build brand recognition in the aural space. Sound effects and music clips can further express a brand in conversational interfaces. Through The Magic Door is an interesting storytelling game that beautifully integrates sounds effects, narration, and synthesized speech to create a branded audio experience.

Conversational interfaces that include visual elements on a screen, like chatbots or GUI voice control, also have a whole range of visual elements to represents a brand. Animated GIFs, emoji, images, and video visually enrich conversational interfaces and are an effective way to convey brand if used correctly.

–

I appreciate conversational interfaces because they provide such a rich and interesting space to create brand and product experiences. There is so much opportunity to build a deeper connection with users through compelling, well-crafted brand experiences.

Written by Lauren Golembiewski, CEO and Co-founder of Voxable. Originally published at www.voxable.io on April 4, 2018.

Branding Bots Part 3: Applying Voice, Tone, & Persona to a CUI was originally published in Chatbots Magazine on Medium, where people are continuing the conversation by highlighting and responding to this story.

SXSW is an other-worldly experience. Austin, Texas, our beloved hometown, becomes unrecognizable. Buildings are transformed to look like sets from movies, live music is around every turn, and celebrities can be spotted reciting poetry on the street. Being equal parts festival, conference, party, and immersive experience, SXSW often feels like spring break for adults. I find it’s a great time to observe trends in the tech industry and get a deeper understanding of where we’re heading so I can navigate Voxable’s course into the future. Here are a few of my takeaways from SXSW this year.

Ethics in technology is a necessity.

The general public, politicians, and entire nations are starting to grapple with the detrimental impact technology, big data, and algorithms can have on our world when design and business are not approached thoughtfully and ethically. It seems like tech companies are failing us left and right in this respect. It’s not just huge corporations; I’ve seen firsthand the way startup culture can prioritize wins for investors over wins for users. When we use capital as the only measurement of value, we deprive ourselves of many ways technology can advance humanity. Since every company in every industry is relying more on technology, it’s paramount for us all to confront the ethical dilemmas that arise with its use.

Discussions about ethics in technology are moving to the forefront, and thought leaders are sharing their perspectives on how to approach ethical design. As a CEO and designer, I believe we need to have more dialogue about the practical implications of ethical design and how to make impactful changes from education on up to C-level decision-making. Even those not convinced by the altruism of ethical design should think about their future consumers — specifically consumers in Generation Z, who are incredibly ethically-minded and seek out products and services that align with their values.

Marginalized people are powerful, yet woefully underrepresented in tech.

I draw so much motivation from getting together with other women to discuss creativity, tech, society, and our experiences in male-dominated workplaces. Recently, there have been a lot of spaces created for women and other marginalized groups to come together to talk about the industry. These spaces are much-needed advancements for inclusion and diversity in tech. However, when we look for real signals of change, we still don’t see them reflected in important areas such as funding, hiring, and promotions.

Issues that impact women and other marginalized people are currently receiving an incredible amount of visibility, but change can take time. We have to remain vigilant if we want to see the change we seek on a large scale. That means we must recognize our personal privileges and biases and work together to find solutions that effectively break down those barriers. On my own perch of privilege, I still struggle to find meaningful ways to be inclusive and support others in the tech industry struggling for representation. I think it’s vital to learn from one another to gain understanding of what it means to be an ally.

Culture is a product of a company’s vision and mission. It’s created at the top.

A vision and mission is the cornerstone of a company. It’s necessary for every company to invest in developing and communicating their vision and mission. Culture arises out of this mission and vision, so it trickles down from the top. In many companies with toxic workplace cultures, there are systemic issues originating from leadership and the lack of a unifying vision and mission.

As the CEO and co-founder of my own company, I place immense value on a clear, purposeful mission and vision. Once solidified, a mission and vision can be the guiding light for everyone — from a company’s leadership and employees to its customers and audience. As technology becomes more intimately woven into humans’ daily lives and consumers demand more ethical design, I predict vision and mission will be a differentiator between companies that succeed and companies that fail.

Design is becoming more complex as we build intelligent and immersive experiences.

As technology advances, brands must determine how to traverse between AI, VR, AR, conversational interfaces, and the plethora of new, relatively cheap technologies gaining market share. Correspondingly, users demand more from digital products as their expectations for service, ethics, and innovation increase. There are young brands like Bumble and Outdoor Voices adeptly crossing this new tech terrain and capitalizing on the immersive experiences their audiences crave.

Design companies now have the impetus to invest in more collaborative, cross-disciplinary processes for building these rich experiences. I recently recognized that having a deep understanding of emerging technology in my field means not only being aware of the interfaces that exist, but also being able to convey their benefits and risks to others so we can approach their design in an ethical manner. I work alongside employees and partners who have a similar viewpoint and want to deliver such innovative, thoughtful products to users.

There is a TON of room for innovation.

One thing that is just as true today as it was yesterday: there is a TON of room for innovation. Surveying the state of tech today, I see so many uncharted spaces to explore and opportunities to make the world better. I’m excited about all the new experiences we can create and technologies we can incorporate into our everyday lives that will allow us to be more imaginative, more innovative, and more superhuman.

I appreciate living in a city that fosters local technological advancement and also hosts massive events like SXSW to bring together global thought leaders across all industries. In Austin, I’m constantly inspired and motivated to innovate. Innovation is about finding ways to make our world better; we do that by evaluating where we are now, considering where we want to be, and imagining how to bridge the two. I know there is a lot of work ahead of us to ensure the technology we build is moving humanity in the right direction. After attending SXSW 2018, I’m optimistic for the future of technology and proud to be a part of the community building it.

Written by Lauren Golembiewski, CEO and Co-founder of Voxable. Originally published at www.voxable.io on March 23, 2018.

The State of Tech in 2018 was originally published in Austin Startups on Medium, where people are continuing the conversation by highlighting and responding to this story.

By now many of you may have heard the newest marketing buzz phrase: conversational marketing. Similar to its omnipresent predecessor, content marketing, conversational marketing is set to shift marketing focus and strategy in a big way.

Let’s take a look at the basics.

Conversational marketing is a way for businesses to engage with an audience through automated one-on-one conversational interactions. This is accomplished through technology referred to as a conversational user interface (CUI), chatbot, or bot.

Conversational marketing leverages the popularity and immediacy of messaging platforms such as Facebook Messenger and enables brands to reach consumers where they spend the majority of their time. Utilizing conversational technology, marketers can deliver content intuitively and automatically through chat interfaces to build their brand and move consumers down the sales funnel.

As a marketer who spent several years knee-deep in automation platforms and refining business email strategy to improve open and click-through rates, it’s hard not to geek out over the opportunities and results conversational marketing affords. Attempting to understand your audience based on information stored in your CRM and deliver personalized, relevant emails using variable data will soon be a thing of the past. Imagine engaging with your audience in a conversation in which they dictate the subject matter and pace while you collect meaningful insight about them in real-time and deliver them the content they want when they want it.

Welcome to the world of chatbots.

Wouldn’t you rather talk with your audience than talk at them? Personally, I’d prefer to participate in a conversation with a brand than be on the receiving end of a one-sided information dump that is rarely relevant to me. Due to the conversational exchange that’s expected by users within messaging platforms, you can learn more from your audience through a minute-long interaction with a chatbot than through weeks of an email campaign. The engagement stats between businesses and audiences further reinforce the allure of conversational marketing as opposed to other marketing strategies (still looking at you, email).

Here are some interesting facts to fuel the conversational marketing fire:

• Monthly active users in messaging apps have surpassed those on social media platforms. (source)
• Average open rates are between 80–95% and click-through rates are 25–30% on Facebook Messenger, the leading conversational marketing platform. (source)
• Gartner predicts that in the next two years, virtual agents will participate in a majority of commercial interactions between people and businesses. (source)

You may be on board to implement a conversational marketing strategy, and you should be, but before you jump in, you need to consider a few things.

The key to marketing effectively in any channel is creating a branded experience that your audience finds engaging and valuable. Many of the out-of-the-box chatbot builders available to marketers right now are clunky and lack the tools needed to satisfy an audience. Since the technology is so new, there are limitations to the current chatbot builder software that hinder user experience and will surely frustrate marketers who have built campaigns in highly sophisticated marketing automation platforms like Marketo, Pardot, or HubSpot.

Unless there’s a developer on your team who has experience building conversational interfaces, you may want to wait until the chatbot builder software improves or hire an agency that specializes in conversational solutions. For those of you who’d rather build a conversational marketing experience yourselves, stay tuned for more blog posts about Voxable’s journey building our marketing chabot, the tools we used, and what we learned along the way.

We are at the very beginning of the conversational marketing era. Therefore, few conversational marketing best practice or strategy guides exist. Similar to social media marketing ten years ago, the lack of conversational marketing documentation and universal understanding of its benefits can make the idea of incorporating it into your overall marketing plan daunting. However, there is huge opportunity in the conversational space and being an early adopter of the technology could translate into a massive return on investment. If you’re interested but unsure how to proceed, consider hiring a conversational interface agency for a consulting session. At the very least, you should start chatting about conversational marketing within your organization.

So the next time you use a messaging application, think about the marketing opportunity at your fingertips. Conversational marketing has the potential to make your brand buzzworthy.

Written by Brittany Walla, Marketing Director at Voxable. Originally published at www.voxable.io on January 19, 2018.

I just finished The Power of Habit: Why We Do What We Do in Life and Business by Charles Duhigg. It’s been on my reading list for a long while, but I finally picked it up on a flight to a conference (traveling is often my catalyst to dig in to new books). I’m really glad I did.

I’ve always struggled with building habits. I chalked it up to having a creative mind — that it’s impossible to form habits AND be a creative person. I needed spontaneity and unstructured play. Or, so I thought.

When I started my career as a designer, effectively honing my skills for business applications, I realized my lack of structure was becoming a downfall. I was bad at keeping a calendar. I was bad at being present in meetings. I rejected such organization because I felt it hindered my creative mind.

As I progressed in my career, I learned the importance of habit and routine. Having daily or weekly check-ins with clients and management built trust among us. Regularly meeting with co-workers to plan and tackle issues was necessary to make our collective effort more impactful. Creativity in the workplace needed guideposts to make sure everyone was working toward the same goal.

I determined I had already formed some habits, but they were not serving me well. I knew I needed better habits, but I was struggling to effectively instill them into my life.

“When a habit emerges, the brain stops fully participating in decision making. It stops working so hard, or diverts focus to other tasks. So unless you deliberately fight a habit — unless you find new routines — the pattern will unfold automatically.”

I still struggle with this, but now I see a way forward — a way to incrementally establish habits that support me in my best professional and personal life. This clarity arose from reading The Power of Habit.

The book has had a profound effect on me, because it doesn’t just cover why habits are important, but how folks build new, better habits. This happens little by little, while still making mistakes, steadfastly sticking to the structure and routines that serve them well.

“First, find a simple and obvious cue. Second, clearly define the rewards.”

Duhigg dives into the psychology of habits and why humans get stuck in bad ones. He tells cautionary tales of the bad habits formed by alcoholics, gamblers, overeaters, and failed companies. Then he explores what is behind habit formation, how we can effectively understand habits and the work we can do to replace them.

“…[To] modify a habit, you must decide to change it. You must consciously accept the hard work of identifying the cues and rewards that drive the habits’ routines, and find alternatives.”

I’ve begun to reframe my thinking about habits. I didn’t miraculously changed ALL my bad habits the moment I finished the book, but I’ve made incremental changes. I’ve begun to better understand my own habits and habit formation.

Changing habits starts with understanding. This book has truly given me a way to observe and understand my habits in a productive way. I’m really excited to apply what I’ve learned to managing Voxable. I know that wrangling our organizational habits will help us grow in a healthy way.

“The best agencies understood the importance of routines. The worst agencies were headed by people who never thought about it, and then wondered why no one followed their orders.

And almost always, they are the products of thoughtlessness, of leaders who avoid thinking about the culture and so let it develop without guidance.”

I recommend The Power of Habit: Why We Do What We Do in Life and Business to anyone who is looking to unlock what’s stopping them from building good habits.

Written by Lauren Golembiewski, CEO and Co-founder of Voxable. Originally published at www.voxable.io on December 20, 2017.

This post is part two of a three-part series on branding bots. Read part one on voice and tone here. We’re diving into how the elements of branding can manifest in conversational interfaces and how companies and products can craft their bot to communicate their brand well.

What is a persona?

In part one of Branding Bots, we discussed how to use voice and tone in conversational interfaces. Persona is the vehicle that delivers the voice and tone of your interface. Persona is all the characteristics of your brand and how it’s expressed to the user. Typically when we think of persona, we’re thinking of a particular character that embodies the brand. Not every brand needs to develop a separate character for their bot, but the characteristics that the bot expresses should be defined.

You may be building the persona as the primary brand mark or as another element of the brand used for specific situations, like in bot dialogue. A well thought-out branding process is necessary to build a strong persona. Research about your audience, competition, and market are essential to creating a persona that resonates with your users.

Why is a persona important?

In conversational interfaces, it’s common to develop a character or mascot as the persona. Because conversational interfaces are… well… conversational, a character is a handy device for engaging in dialogue with a human. Having a conversation with a defined character is easier to do than having one with a company name or logo. Folks empathize more with characters that have traits similar to their own. In fact, humans have a tendency to anthropomorphize objects and characters that they’re having a conversation with, especially in a voice interaction. Building and controlling that character is better for your brand than leaving it up to the user’s imagination.

A character or mascot may not always make sense for your brand, and that’s OK. You should still pay attention to the way that your brand is communicating and make sure voice and tone are consistent.

The psychology of personas

There are a few psychological devices that you can use to craft your bot’s persona. These can help you design and test a persona for your bot to find what is most useful to your audience.

Themes and forms that are a part of our cultural biases can play a major role in building personas in a brand. Psychologist Carl Jung developed the concept, and his idea derived from thinkers and philosophers before him like Kant and Plato. He thought that characters or archetypes are immediately familiar to us because they are innate in our culture. Archetypes help set expectations and give your brand broader meaning. We have been using them in storytelling for ages, and you can still see them in films and stories we tell today.

Brands like Nike use the Hero archetype while the Harley Davidson brand uses the Outlaw archetype. A persona can build on these familiar themes to engage with your audience more effectively. A brand does not have to choose only one archetype and it can use aspects of a few of them together.

Stickiness

Malcolm Gladwell talks about stickiness in The Tipping Point; it’s the ability for ideas, or in this case, a persona to become crystallized in pop culture. The six elements that are important in creating a sticky brand are Simplicity, Surprise, Concreteness, Credibility, Emotion, and Story.

Storytelling

Storytelling can be quite compelling if you move past the buzzword and put in the work to build a great story. Using the elements of storytelling has been an effective means of communication for millenia, and we can employ it in creating a bot’s persona. Stories can help users understand complex ideas and help them more deeply empathize with the persona. The elements of storytelling are Setting, Plot, Characters, Invisibility, Mood, and Movement. Cabbage Patch Kids became the 80s toy craze that it was because their brand developed stories for their dolls, complete with a birth certificate and adoption paper for each doll.

Baby-Face bias

The baby-face bias is the propensity for humans to be attracted to forms that have baby-like features like big eyes, small noses, high foreheads and small chins. We can see this effect even in non-human forms. Think of little Groot from The Guardians of the Galaxy — totally baby face that makes you go “Awwww.” Think about using the Baby-Face Bias when building the avatar for your brand as it may help users forgive your bots mistakes, too.

Similarity bias

Similarity Bias is the tendency for humans to like and trust other people and things that are similar to them. Wired for Speech describes a study in which introverted and extroverted subjects interacted with voice interfaces that exhibited introverted-ness and extroverted-ness. Those who interacted with the interface that matched their disposition (introverted subjects interacting with introverted interfaces) were more likely to rate the information those interfaces delivered as credible. Knowing your audience and their personality traits could have a significant impact on your brand’s personality.

Gender

As you develop your character, you have to consider its gender or lack thereof. In a chatbot interface, gender can be ambiguous and doesn’t need to be clearly defined. The persona may never acknowledge gender at all, which works well in a text-based interface. However, interfaces that users experience through voice will have a gender associated with them regardless of the brand’s intent. Humans are wired to assign gender to voices. Even if there is a gender neutral persona, the voice of the persona often dictates how the user perceives it.

It’s also important to consider the social implications of gender while creating a brand. Discussion of sexism is varied and vibrant in the context of bots. Brands should carefully consider gender, or lack thereof, and how that weaves into the brand story. Designers should be cognizant of how gender relates to users. Brand owners and designers should prepare themselves to field questions and have conversations about the chosen gender of their bot.

💡 Tip: The persona of a chatbot should never lead users to think that it’s an actual human. It should be clear to the users that they are speaking with a bot. Designers should be especially cognizant of times when a user might expect to be speaking with a human but are actually speaking to a bot, like in support situations.

Now let’s talk about the UI elements available in conversational interfaces to express a persona.

Display name or invocation name

On a platform like Facebook Messenger, the display name of the page your bot lives on will be the name that shows up in a chat conversation. Many brands consider building a new brand personality for a bot, but may not be ready for that personality to take over their social media presence. Some consider creating new Facebook pages, or they stick with their primary brand before diving into persona development.

On voice interfaces, the bot’s name is called the invocation name, because this is what users will say to direct Google or Alexa to talk to your bot. Alexa and Google place some restrictions around the invocation name. Some of those rules are that they have to be real words, but not one-word names, cannot be common phrases, cannot be proper nouns, must be unique, and must be phonetically distinct. Consider these factors before building a persona that won’t work as an invocation name.

Avatar

On Facebook Messenger, the avatar you set for your Facebook Business Page will be the avatar of the bot in conversation. The avatar should be the same as the persona, but that may create some friction between your established brand and the new bot persona on social media profiles (just like the display name).

Voice interfaces like Google Assistant and Amazon Alexa both have avatars shown in their bot libraries, and Assistant uses avatars in the conversation threads in the app. The avatar sets the first impression and can be used in many places to communicate your brand, like email, so building a great avatar is important.

Voice selection

For the two leading voice interfaces, Google Assistant and Amazon Alexa, there are different offerings for synthesized voice.

Alexa

Alexa has a defined female voice that designers and developers cannot change. Alexa is the assistant that users are asking to carry out the particular action your skill provides. It places your bot in the domain of Alexa’s persona, and the general assistant asks your bot to perform the task.

Google

Actions on Google provides a set of four voices designers can choose to use in an action. While the Google Assistant maintains the same female voice, third-party Actions on Google are allowed to respond in a different voice. The available voices include typical male and female voice ranges. Google Assistant acts as more of a DJ, serving up the various bots users request, and handing over control to those bots until the users achieve thier goals.

I suspect that voice selection will become more varied as voice synthesis gets better and better. Check out Lyrebird, a voice synthesis API that can mimic actual human voices. The voices our interfaces use will become as varied as all of our voices, so the possibilities could be endless.

Hearing the voice interface is the only way to judge the medium. I find that it’s helpful to play-act your voice interfaces to help sketch out your persona. If you can build a prototype to hear the bot’s personality in the synthesized voice, that help you better judge the effectiveness of your persona.

Persona that moves the brand forward

Like any design process, building a persona can be daunting. Good brand designers should be able to help guide you to make sure your persona is consistent and that it aligns with the qualities you want it to express. Even if you are only using the devices we’ve discussed to give internal guidance, a solid persona will help users identify with it.

At Voxable, when we start to build a persona for a bot, we usually start out with a thought experiment: “If this piece of technology were an actual character or human that was carrying out these tasks, how would they talk to the customer?” This experiment helps us understand the domain of the persona and the situations to which it may have to react. As we dig into research about our users, competitors, and market, we start to get a better sense of what personality traits we want our persona to embody. Keep in mind that you can always test your persona with users. Because voice selection may be varied and broad, user testing a prototype will help you understand how it affects your audience.

Stay tuned for part three of Branding Bots, where we talk about the key moments that can make and break your bot’s branding.

We’d love to hear your thoughts on branding bots and how you’ve used voice and tone to communicate through them. Hit us up on Twitter @voxable.

Stay up-to-date on all the bot knowledge Voxable drops. Sign up for our email list, and we’ll deliver our best insights about designing and building conversational interfaces right to your inbox.

Written by Lauren Golembiewski, CEO and Co-founder of Voxable. Originally published at www.voxable.io on June 29, 2017.

At SXSW 2017, as a part of our session “The History and Future of Speaking with Machines,” Matt gave a talk about how to build an action on Google in under 10 minutes. He goes from selecting an API and creating a Natural Language Understanding model in API.ai, to connecting that model to an API. You can remix this project on Glitch today.

We are excited about the Actions on Google Platform for Google’s powerful Assistant. Assistant is available on the Google Home as well as in the Assistant App and Allo messaging app. We are thrilled to be building some amazing bots in the Google Assistant for our client’s products and our own.

API.ai makes getting started with building voice interfaces really easy. The platform has an easy-to-use interface along with one-click integrations to connect your agent to the Google Home, among several other platforms.

Watch the video to see how easy it is to get started!

Transcript

When I was thinking about what to do for this demo, I had a few decisions to make. One of those was what platform I wanted to build for. I decided to go with the Google Home, which we talked about a bit, earlier. I also needed to make some decisions around which API to use. For those of you unfamiliar, API; Application Programming Interface. We’ve been talking about how humans speak to machines. APIs are how machines speak to one another. That’s how different computer systems can share data with one another.

So, I decided to build for the Google Home. When you’re building for the Google Home, you actually get to use this Actions on Google framework. This was released late last year. This allows you to give the Google Assistant, which is Google’s Personal Assistant AI, new abilities — teach it how to do new things. A lot of the work of building voice interfaces, we’re translating human speech into a series of API calls, really. So, I needed to find a cool API, that could do something interesting.

I found this one here. It’s called the College Scorecard. This is a free API put out by the federal government. It gives you information on various public Universities, and it tells you lots of different data, that they’re required to report to the federal government. I thought “Okay, cool. This is handy.” It might be useful for someone applying to college, to be able to say “Okay, Google. Ask college advisor for the acceptance rate at the University of Texas, at Austin.” I set out with that goal in mind, sat down, and got something built really quickly. I thought “Hey, this is really cool! It works.” Now, what I neglected to do was just ask Google the question, “What is the admission rate at the University of Texas?”

When you do that, you’ll see that it answers it for you in this little Answer box. It knows the answer. So, that means if you just ask your Google Home “Hey, okay, Google. What is the acceptance rate at the University of Texas?” it already knows how to answer that question. So, lesson one, when building for the Google Home: if you think you’re teaching Google a new trick, make sure that it doesn’t already know how to do that trick.

I set out to find a new API, and I found this one here. It’s called An API of Ice and Fire. For those of you familiar with Game of Thrones, this is a Game of Thrones API. It’s pretty cool. It gives you lots of information about the characters.

I’m a fan of Game of Thrones, and in the show, even more so in the books, there are a lot of characters in these books. Not only that, but each character is known by like eight or nine different names, to makes things even easier.

So, I thought “Hey, wouldn’t it be cool if I could say ‘Okay, Google. Ask Westeros Directory Services for Petyr Baelish’s other names,’ and it would just give me a list of aliases.” So, now that we have an API like this, and we have a decision on what it is that we want to build, let’s see if we can get this done. We’ll put ten minutes on the clock, and let’s go.

I’m here in API.ai. This is an NLU platform that was acquired by Google last year. That’s Natural Language Understanding. I’m going to create myself an agent in API “WesterosDirectoryServices.” An agent is kind of where we house all of the NLU for the particular project that we’re working on.

So, I need to create myself an Entity. We talked about these earlier, right? These are the data that we pull out of something that’s said. If someone asks “Ask Westeros Directory Services for Arya Stark’s other names,” Google is going to send to API.ai; not that invocation, not the “Ask Westeros Directory Services,” but the “Arya Stark’s other names” portion of that.

We’re going to need to pull that character name out of the speech, right? So, I need a character Entity. I’ll create one for Petyr Baelish. That might be mis-heard by the speech detect system, as Peter with an “e,” since that’s how we spell it on Earth. “Peter Baelish.” I’m just entering synonyms; different ways that might be heard.

And then, Arya Stark, that might be heard as “Aria” with an “i.” The reason that that’s important and we can see, if I switch over to Postman, if I call this API with Arya with a “y,” it understands. If I call it with Aria with an “i,” it doesn’t know what we’re talking about.

This is called “canonical entity values,” right? So, each one of these entities has this name, and only this name. If you hear it as this, give it to me as Arya with a “y.”

Now, we’ll need an Intent. An Intent, these are all the various things in a system that a user might want to do. In this case, they’ll want to list the aliases. They might say “Arya Stark’s other names.” You can see it’s automatically already understanding. “Oh! That’s that character Arya Stark you taught me about earlier.” “Is Petyr Baelish known by any other names?”

Here, I’m just entering all the various ways someone might ask this question, and it’s going through and annotating those to show me the Entities I’ve already created. I’ll give this an Action name of “listAliases.” Actions become more important when you get into more in-depth features like dialogues, but we’ll just use this to route to the appropriate code. I can enter a response here, if I wanted. “Arya is also known as Jill or Susan.” I can save that, and now, let’s give this a shot.

“Petyr Baelish’s other names.” You can see, this understood what I said. It actually heard it as “Petyr Baelish is other names,” but API.ai was smart enough to figure out what we were going for. It figured out we wanted that listAliases action. It pulled out that character of Petyr Baelish.

Oh, no! But it’s telling us that Arya is also known as Jill or Susan. We can’t use a static response there, right? We need another API that’s then going to call out to the API of Ice and Fire, find out Arya Stark’s other names, and then generate some kind of a response that we should respond with actual speech, back to the user.

In order to do that, I’m going to have to use this feature of API.ai called Fulfillment. First, I’ll save my Intent, there. We’ll go down to Fulfillment, turn this on. It wants a URL, so we’re actually going to need to build our own API.

For that, I’m going to use this project called Gomix (note: this is now called Glitch. Gomix, if you haven’t heard of it, it’s very, very cool. It’s a live IDE, a live code editor in your browser. What’s interesting is, as you make changes to the code, it’s automatically re-deploying your project. So, not only do you get to edit your code, but you already have it deployed. It’s a really fun way to kind of try things out.

So, we put together this Actions on Google API.ai Boilerplate. After the talk, we’ll tweet out a link to that. All you have to do is click this “Remix This” button, and then, cool! I’ve got my own version, my own API sitting here, waiting for me to code on it.

Now, I’ll head over to the server.js, and start checking out the code. Okay, it looks like it’s an express app, so if you’re a JavaScript developer, this is familiar. We’re posting, okay, it looks like this was asking the weather. So, you could grab the city. “What’s the weather like in Austin?” It’s going to make a call to the Yahoo Weather API, and then it’s going to pull some data out of there, and generate a response.

I think I see what’s going on here. So, first of all, let’s do a LIST_ALIASES_ACTION, right? That’s the one for ours. That’s listAliases. So, we have a few other places now, in the code, where it’s going to tell me, if I just follow my linter.

Okay, so I need — there. That looks like that’s where we’re routing to LIST_ALIASES. In fact, I’m going to call this function listAliases, so we’ll route to this listAliases handler function. Okay, and then I need a, so that’s going to be a CHARACTER_PARAMETER. That, we just need to switch to character.

Same deal, right? We’ve got another place where we’re pulling that parameter, that entity, out, so we’ll say let character.

Here, we don’t need this URL anymore, but we do need a requestURL, and we’ll make this. We’ll grab it right from Postman. So, I can’t hard code Arya Stark in there; we’re just going to get her names back every time, so I’ll actually just pass in that character name we just grabbed.

Cool! Now, I’ve generated the proper URL. Let’s make a request to that URL, and rather than pulling out units and temperature, like we’re doing here, we just need the aliases from that response. If I look at the response, it looks like we’ve got an array, and at the first element, we need the aliases attribute. Okay, cool. I’ll say body, and at the first element I have got an attribute aliases. So, there are my aliases. We’ll take that out of the code.

And then, okay, assistant.tell. This looks like this is where we actually generate a response, so we’ll say assistant.tell(character + ‘ is also known as’), and then we’ll use the toSentence method I included for us, (aliases). Okay, so let’s pull that response out. Let’s check our linter again. It looks like we shouldn’t have any errors, and we’re properly routing down here, from LIST_ALIASES. Great!

Now, I’m going to need that live URL. So, if I just click Show Live, grab that URL, come back here, we’ll enter that as the endpoint URL. Now, I’ll head back to my Intent for LIST_ALIASES, and I’ll say rather than using that static response, I actually want to turn on this webhook fulfillment. We’ll save that, give it a moment to update, and let’s try it again.

“Petyr Baelish’s other names.” Cool! So, that came down, and it grabbed the Intent listAliases and the action listAliases. Let’s try one more time. “Arya Stark’s other names.” Cool! It took the model a moment to update, but now you can see it’s actually grabbing our response from that API that we created, right?

Let’s see if we can get this hooked up to a Google Home device. We get all these one-click integrations in API.ai. I’m going to activate the one for Actions on Google. I’m going to give it the name — let’s turn that on — I’m going to give it the name Westeros Directory Services. I can choose different voices, if I’d like things like that, but I’m just going to go ahead and authorize, and preview that.

Now, this is actually deploying this to something called the “Google Home Web Simulator.” The Web Simulator is really interesting. It’s a place where I can actually test my Google Home actions, just right here in the web. I’ll make sure that’s reloaded the proper action, and let’s give this a shot.

“Ask Westeros Directory Services for Arya Stark’s other names.” “Sure, here’s Westeros Directory Services. Arya Stark is also known as Arya Horseface, Arya Underfoot, Arry, Lumpyface, Lumpyhead, Stickboy, Weasel, Nymera, Squan, Saltb, Cat of the Canaly, Bets, The Blind Girh, The Ugly Little Girl, Mercedent and Mercye.”

Do you see what I’m talking about? Ridiculous! Why does one character need this many names?

So, yeah. I don’t know. By the way, has HBO been doing any marketing for Game of Thrones? Someone should talk to them, because I feel like they should really be here, telling people about that show.

That was 07:42, so we did it, y’all! We did it! Less than 10 minutes! We were able to go from idea to an actual machine that can answer our weird, nerdy questions, that we just came up with.

There’s a lot of stuff we could do, to go from here, right? We could use some API.ai features like Context, so we could do things to ask follow-up questions, like “Okay. What’s her mother’s name?” In that sentence, I’m going to need to understand what that pronoun “her” is referring to, right? It’s referencing the character we just asked about.

There are a lot of places we can go with this. I hope you’ll check out the Boilerplate Project, but the fact that we’ve gotten here, after this many centuries, represents not only a monumental achievement in the history of computing, but in the history of the grand conversation between humans and machines.

We can’t wait to see what you’ve built!

Thank you so much.

Voxable helps companies and products understand the conversational commerce landscape and build bots to help them automate conversations with their teams and customers. We build all things that help humans talk to machines, including chatbots for major messaging channels, Alexa Skills, and bots for the Google Assistant. If you’re interested in building a conversational strategy, holler at us!

Written by Matt Buck, CTO and Co-founder of Voxable. Originally published at www.voxable.io on May 25, 2017.

Branding Bots Part 1: Crafting Voice & Tone For Your Chatbots & Voice Interfaces

This post is part one of a three-part series on branding bots. We’re diving into how the elements of branding can manifest in conversational interfaces and how companies and products can craft their bot to communicate their brand well.

Great bots have the ability to pull you in and connect with you emotionally, but bots need great branding to be successful. Building a great brand starts well before you design the bot’s interface (or any other interface to which you deliver your product).

Great brands can transform an experience and evoke emotion in you. Brands can make you laugh, feel sad, or take action. They express human qualities that we associate with those companies. We can all think of examples of great brands and which traits we associate with them.

Branding happens whether you plan it or not; it’s every single way that you communicate with your audience. A careful branding process backed by proper research and plenty of decision-making produces an outcome that is greater than the sum of its parts.

“Branding happens whether you plan it or not. It’s every single way that you communicate with your audience.”

Great branding considers the most effective ways to communicate and then carefully crafts visual and textual elements that will best deliver that communication. Brands include elements like a mission statement, marketing direction, language structure, colors, fonts, images, and an identity system (logo or series of logos).

Like any other product, if a bot’s branding is not clear and consistent, the experience will fall flat. Companies and products need to consider how their existing product brand extends to a conversational interface. Companies whose primary interface is a bot need to establish a strong conversation-focused brand.

Designing your first bot is a great opportunity to embark on your first branding exercise or to reevaluate your current brand system.

Whether you already have a well-established brand that you’re extending to a bot or you’re building it from the ground up, chatbots and voice assistants have particular devices for brand expression. In this post, we’ll cover how your bot branding can use voice and tone to communicate with your audience.

Voice and Tone

Voice and tone are an important part of any brand, but conversational interfaces like chatbots or voice assistants rely on it heavily. First and foremost, they are textual interfaces that build a conversation with the user, and the voice of that conversation and the way that the tone adapts to the state of the conversation is important.

The core values and mission of the company are the pillars of the brand’s voice. Voice should stay consistent and in alignment with the company’s values and mission. Bots are like an ambassador for the brand and they have to engage appropriately. The voice of a bot can be sarcastic, cheerful, or any other qualities you think reflect the core mission and values of your company.

“Bots are an ambassador for the brand and they have to engage appropriately.”

If you haven’t established a clear voice for your company, several resources can help guide you on your way. This explanation of Clearleft’s language refresh is a great example of (re)building voice and tone. Mailchimp has a fantastic content style guide (for their super-effective brand) that puts a lot of emphasis on voice and tone.

Tone builds off of voice and it shifts with the state of the conversation and the emotional condition of the user. Tone helps conversations seem natural. After you’ve crafted a solid voice, then you need to consider when and how your tone modulates.

Here is how we consider the tonal shifts in conversational interfaces:

The Possible Emotional State of the User

Technology is pretty amazing, and advancements in Natural Language Understanding (NLU) allow us to extract sentiment from users’ language. Sentiment Analysis returns a positivity score on a string of text entered by a user. Additionally, tools like IBM Watson’s Tone Analyzer allow us to get a more nuanced view into the tone and style of language.

If you’re starting small, and don’t want to integrate additional services like Tone Analyzer, there are plenty of options to help you make an intelligent guess about a user’s emotional state. Performing user research and analyzing the user experience will help you understand how the emotional states of your users shift as they interact with your bot.

• 🤔 Confused — when instructions are not clear, or users aren’t sure how to make a decision.
• 😖 Frustrated — when a user cannot complete a task, or they can’t find something in the interface.
• 😆 Delighted — when a user finds success in the interface or has accomplished a goal.

The State of the Conversation

A natural conversation relies on a shared understanding, and bots and users build understanding throughout the conversation. When a user replies, “yes,” the bot needs to know specifically what the user is confirming. The shared understanding your bot builds with the user affects the language your bot uses.

• Asking for a response that confirms an action
• Signaling understanding of what the user has said
• Requesting more information to complete a task

The State of the System

As the user interacts with the bot, the state of that system, or the data that underlies it, also changes. Communicating these system changes to the user is important. Modulate the bot’s tone so that the user’s emotional reaction is as positive as possible.

• Errors — Be clear about who is responsible for an error and how the user or the bot will resolve it. Make sure the tone is appropriate, especially if it’s your system that is causing the failure.
• Success — Noting the end state, especially success, is important for the user to acknowledge when they’ve reached the end of a task or accomplished a goal.
• Processing — Let the user know when a process is being carried out and how long it should take.

Delivery Method

Delivery through a chat platform like Facebook Messenger versus a voice-based device like the Google Home also should have an effect on your language.

• Text-based conversations — Chat platforms have visual feedback and a temporal record of previous interactions. A bot can deliver other media like images and video that amplifies the meaning of a text response.
• Voice-based conversations — Since there are little to no visual elements that accompany interaction with devices like the Amazon Echo or Google Home, the communication context shifts for users. You must optimize your bot’s language for vocal delivery.

💡 Tip: Be sure you write the language of a Voice User Interface (VUI) like an Alexa Skill or Actions on Google for speaking. Read the interface scripts out loud as a role-playing exercise to assess and refine the bot’s responses.

The Elements of Conversational Voice & Tone

Chatbots

In addition to text, bots built for messenger platforms have some other affordances that help convey voice and tone. The support for these elements depend on the platform for which you’re building, but here are the most popular:

• Emojis
• Video and animations
• Images
• Audio clips

VUIs

Although VUIs provide little to no visual interface for elements to convey voice and tone, they do have several affordances that reflect the brand:

SSML or Speech Synthesis Markup Language gives you affordances within the language of your bot that help you modulate the way the voice interface speaks. You can adjust elements like speed, pitch, and pauses with SSML. ⚙️ Supported by Alexa and Google

Some voice interface platforms allow you to choose from a set of synthesized voices for your bot. You can also hire voice actors to record all the possible conversations your bot might have. Though this is a lengthy and expensive process, it allows for ultimate control over the bot’s vocal brand. ⚙️ Synthesized voice selection supported by Google

Voice platforms come with companion mobile apps. Alexa’s mobile app supports the use of cards along with your Skill. These allow you to deliver images and text to the user when they interact with your Skill. ⚙️ Supported by Alexa

You can use audio clips like tones, sounds, and music throughout your voice-based bot. These can provide brand elements like intro music or help ground the user with sound effects. ⚙️ Supported by SSML on both platforms

Speechcons are predefined words and phrases spoken with particular emphasis that you can build into your Alexa Skill. ⚙️ Supported by Alexa

Crafting an experience that effectively uses these elements will take some experimentation and iteration. Don’t pressure yourself to create an exact definition of how the brand uses all these elements until you have a feeling for how they’re all working together. This is process that takes a great deal of work, so start with understanding all these tools for branding conversational interfaces.

This post provides a starting framework for developing voice and tone in your bot. There are several decisions that you will make as you outline how your bot delivers the core capabilities of your product to your users. If your product offering shifts, it is a good idea to make sure your voice and tone align to your product’s promise.

You may also be considering building a persona that embodies your bot, which can be an effective way to express voice and tone in bots. Part 2 of Branding Bots will cover how you can use personas for your bot’s brand.

We’d love to hear your thoughts on branding bots and how you’ve used voice and tone to communicate through them. Hit us up on Twitter @voxable.

Stay up-to-date on all the bot knowledge Voxable drops. Sign up for our email list, and we’ll deliver our best insights about designing and building conversational interfaces right to your inbox.

Written by Lauren Golembiewski, CEO and Co-founder of Voxable. Originally published at www.voxable.io on April 18, 2017.

Branding Bots Part 1: Crafting Voice and Tone For Your Chatbots and Voice Interfaces was originally published in Chatbots Magazine on Medium, where people are continuing the conversation by highlighting and responding to this story.