Book description
If you're a new or experienced designer of conversational voice first experiences, this handy reference provides actionable answers to key aspects of eyes-busy, hands-busy, voice-only user interfaces. Designed as a companion to books about conversational voice design, this guide includes important details regarding eyes-free, hands-free, voice-only interfaces delivered by Amazon Echo, Google Nest, and a variety of in-car experiences.
Authors Ahmed Bouzid and Weiye Ma provide far-field voice best practices and recommendations in a manner similar to The Elements of Style, the popular American English writing style guide. Like that book, The Elements of Voice First Style provides direct, succinct explanations that focus on the essence of each topic. You'll find answers quickly without having to spend time searching through other sources.
With this guide, you'll be able to:
- Craft just the right language to enable your voicebot to effectively communicate with humans
- Create conversational voice interfaces that are robust enough to handle errors and failures
- Design highly usable conversational voice interfaces by paying attention to small details that can make or break the experience
- Build a design for a voice-only smart speaker that doesn't require customers to use their eyes or hands
Publisher resources
Table of contents
- Preface
- Introduction
- 1. Why Voice First
- 2. When Voice First
- 3. Why Voice First Automation
- 4. The Three Core Characteristics of the VUI
- 5. The Elements of Conversation
- 6. The Rules of Conversation
- 7. The Basic Tenets
- 8. The Extra-Conversational Context
- 9. The UI Use Case Fit
-
10. The Elements of Starting
- Be Brief
- Use an Audio Icon
- Drop the “Welcome to…”
- Never Ever Say, “Please Listen Carefully as Our Options Have Changed”
- Have the Voicebot Refer to Itself in the First Person
- Drop “You Can Interrupt Me at Any Time”
- Keep the Origination Context in Mind
- Remember the User’s Preferences
- Anticipate User-Specific Requests
- Anticipate General User-Base Requests
-
11. The Elements of Prompting
- Prompt Types
-
Writing Effective Prompts
- Use Language That Is Commonly Used in Conversations
- Remember That the User Will Mimic the Voicebot
- Unless It’s Essential to the Use Case, Don’t Use Slang or Jargon
- Put the Most Important Information First
- Use Want Instead of Wish
- Avoid Using Speak
- Use Contractions
- Be Consistent in Your Wording
- Avoid Mixing Recorded and TTS Speech
- It’s OK for a Sentence to End in a Preposition
- Avoid Using Whom
- Minimize the Use of Please
- Use Incremental Prompts When Dealing with Expert Users
- Use Tapering Prompts to Minimize on Wordy Repetitions
- Request an Explicit Confirmation Only When Necessary
-
12. Choices
- Present the Most Requested Items First
- Keep the Menu List to Three Items or Less
- Keep the Menu Depth to Three Levels or Less
- Avoid the Construction of “for/to X, Say X; for/to Y, Say Y; for/to Z, Say Z”
- Don’t Use, “Please Select from the Following Options”
- Use the Same Part of Speech/Clausal Form When Listing Menu Options
- Let Users Ask, “What Are My Choices?”
- Let Users “Climb Back” the Menu
- Offer to Repeat the Menu Options After a 3-Second Pause
- Turn on Barge-In for Expert Users
- Include and Teach Shortcuts
-
13. Managing Failure
- Types of Failure
- Causes of Failure
-
Best Practices
- Always Have the Voicebot Take the Blame
- Give the User Three Chances
- Offer Explicit Examples of How to Respond
- Be Careful When You Reprompt
- Establish “Safety Points”
- Never Terminate a Conversation Unilaterally—Especially During Recovery
- Don’t Be Repetitive During Recovery
- Orient the User About Where They Are
- Give the User Information About the Issue
- Do Not Be Overly Apologetic
- 14. Help Strategies
-
15. Verbal Dialogue Marking
- Acknowledge Receipt of Information
- Announce That the User Is About to Receive Some Information
- Mark Sequences
- Mark the Beginning and End of a Section
- Mark Failures
- Show Light at the End of the Tunnel
- Indicate Implicitly That the Voicebot Still Owns the Turn
- Tell the User Explicitly That They Are Being Placed on Hold
- Don’t Repeat the Same Marker Twice in a Row
- Pay Attention to the Markers After a Failure Strategy
-
16. Nonverbal Dialogue Marking
- Types of Nonverbal Audio
- Opening the Dialogue
- Signaling That It’s the User’s Turn to Speak
- Signaling That the Voicebot Is Busy Doing Something and Is Holding the Turn
- Waiting for the User to Give an Answer
- After a No-Input
- Announcing a List of Choices
- Entering a New Section
- Marking Transition from One List Item to the Next
- Announcing Help
- Ending the Conversation
-
17. Language Design
- On “Naturalness”
- Key Terms
- Designing an Effective Language Model
- Clearly Define the Problems That Your Voicebot Can Help the User With
- Communicate Why the Voicebot Exists and What It Can Help the User Do Outside of the Voicebot
- Spend Time Building a Clean Ontology
- Do Not Design Your Language from the Armchair
- Go Explicit When Recovering from a Language Error
- 18. On Silence
-
19. The Elements of Closing
- Allow the Users to Explicitly End the Dialogue
- Allow the User to Request a Human
- When the User Has to Wait, Provide a Waiting Time Estimate
- Provide the Option to Cancel a Transfer to a Human
- Keep the “While-You-Wait” Audio Relevant
- Understand the User’s State of Mind When You Play the “While-You-Wait” Audio
- Never Say, “Your Call Is Important to Us”
- Don’t Make the User Repeat to the Human Information They Provided to the Voicebot
- Make the Human Agent Aware That the Customer Was Interacting with the Voicebot
- Avoid Transferring Users from One Voicebot to Another
- Don’t Play Phone Rings Unless You Are Transferring Directly to a Human
- Reassure Users of Success
- Don’t Provide Any Crucial New Information
- Give the User a Quick Tip
- Offer to Reach Back
- 20. Voice First Notifications
- 21. Laying Out the Foundations
-
22. The Key to Successful Product Launches
- Write Everything Out in Full Sentences
- Your Press Release Needs to Be Crystal Clear
- Your Answers Are Given in One or Two Paragraphs at Most, and Not Much More
- Answer the Basic Questions First
- Describe Clearly the Research You Have Done
- Be Modest and Cautious in Your Claims and Statements
- Make Your Document Readable by Everyone
- List the Functional Requirements in Terms of What the User Can Do
- Describe the Intended Minimum Viable Product (MVP) in Detail
- 23. The Elements of Deployment
-
24. Post-Launch Monitoring
- Sources of Information
-
The Basic Questions
- Where Are Users Abandoning the Session?
- Where Are Users Asking to Be Connected to a Human Agent?
- Where Are Users Saying the Wrong Things?
- Where Are Users Not Saying Anything?
- Where Are Users Speaking Too Soon?
- What Is the Noise Level of Your User’s Environment?
- What Options Are Your Users Asking For?
- How Are Users Feeling About the Voicebot?
- 25. The Elements of Voice First Success
- 26. Coda
- A. The 10 Sources of Voice First Failures!
-
B. Demonstrating Voice First
- Remove All Prompts That Explicitly Talk About Failure
- Don’t Speak Over Prompts
- Don’t Have the Voicebot Talk for More Than 10 Seconds When It Starts Without Giving the Turn Back to You
- Test the Voicebot with the Same Equipment You Will Use in the Demo
- Have Two or Three Backup Ways to Demo the Voicebot
- Test the Application in the Same Room and Environment Where You Will Do the Demo
- Know How to Gracefully End a Telephony-Based Voicebot
- Ask for Silence
- Never Improvise or Show Off While Demoing
- If, for Whatever Reason, the Voicebot Fails, Be Honest About Why It Failed
- No Cheat Sheets!
- Speak Normally
- Don’t Leave Long Silences Between Words When You Speak
- Keep It Really Short
- C. Useful Matrices
- A Voice First Glossary
- References
- Index
- About the Authors
Product information
- Title: The Elements of Voice First Style
- Author(s):
- Release date: May 2022
- Publisher(s): O'Reilly Media, Inc.
- ISBN: 9781098119591
You might also like
article
Communicate with Teams More Effectively
This selection of shortcuts will enable you to improve your communication, critical thinking, documentation, and networking …
book
Mastering Voice Interfaces: Creating Great Voice Apps for Real Users
Build great voice apps of any complexity for any domain by learning both the how's and …
audiobook
The Year in Tech, 2025
<B>A year of HBR's essential thinking on tech—all in one place.</B><br/><br/><br/><br/>Generative AI, biometrics, spatial computing, electric …
article
Become a Better Problem Solver by Telling Better Stories
One of the biggest obstacles to effective problem-solving is not defining the problem well. Invoking the …