Voice Glossary

Consumer-facing AI systems can carry out tasks or services for an individual based on commands or questions.

A credential that represents the end user (resource owner) in another system. A token should identify the user in the other system. The access token is included in the requests sent to your skill if the user has successfully linked their accounts. (Source: Alexa glossary)

An Alexa Skills Kit feature that lets you connect the identity of the end user with an account in another system. For example, a Car Hailer custom skill for ordering a ride needs to access the Car Hailer service as a specific user. Similarly, a smart home skill for controlling a light needs to connect the Alexa user with an account in the device cloud. (Source: Alexa glossary)

A JSON file that defines your Actions. This file includes information for the Actions directory listing, account linking information, a list of intents that the Actions can handle, and the actual fulfillment endpoints.

A phrase that opens a specific action when spoken to a Google Assistant. Also known as the "invocation phrase" or "implicit invocation intent". An example of this would be "Ok Google, open Trivial Pursuit".

A web tool for testing and debugging Actions in real-time. The simulator lets you test your Actions for all surfaces that the Google Assistant supports, without requiring a physical device.

Amazon has created a development tool that allows you to create, modify and delete skills. Coding required.

The Alexa Developer Console is a conversational platform that allows developers to build, test, distribute and certify Alexa Skills.

This is Amazon's voice-first design language that makes it easy to create visually-rich Alexa skills for millions of Alexa devices with screens. APL enables creators to build interactive voice experiences that include graphics, images, slideshows, and video and to customize them for different device types such as Echo Show, Fire TV and select Fire Tablet devices.

A set of actions or tasks that are accomplished by Alexa — Amazon's voice assistant. Skills are like apps for Alexa. They help customers perform everyday tasks or engage with content naturally through voice.

A collection of APIs, tools and documentation for giving Alexa new capabilities.

Amazon Connect is an omnichannel cloud contact center service that provides a seamless experience across voice and chat for your customers and agents. This includes one set of tools for skills-based routing, powerful real-time and historical analytics, and easy-to-use intuitive management tools.

A service that turns text into lifelike speech, allowing you to create applications that talk, and build entirely new categories of speech-enabled products. The text-to-speech service uses advanced deep learning technologies to synthesize speech that sounds like a human voice. With dozens of lifelike voices across a variety of languages, you can select the ideal voice and build speech-enabled applications that work in many different countries. (Source: Alexa glossary)

This is a term used to describe a state where technology is omnipresent and accessible whenever required.

This is code that allows two software programs to communicate with each other.

Stands for "applications". Apps are pieces of software written for a specific platform that are meant to do a particular task. For example, on the iPhone platform, you could create a calculator "app" that utilizes the software and hardware in the iPhone.

An application with interactive voice response (IVR) systems that automatically answers, directs, and transfers incoming calls to an extension without the need of a phone operator/receptionist.

Computer technology that can identify and process human voice. It is mainly used to convert spoken words into computer text. ASR is also used for authenticating users via their voice and performing an action based on the instructions defined by the user. Typically, automatic speech recognition requires preconfigured or saved voices of the primary user(s). It is also known as Automatic Voice Recognition (AVR)

Caller intent identifies the reason for each phone call, thereby uncovering opportunities to personalize customer engagement, and to predict customer actions.

Programs that automate conversations on web or instant messenger

The total amount of mental effort being used in the working memory, or how difficult it is for a user to understand or parse the information being presented to them. (Source: Alexa glossary)

When Alexa says something to make sure the customer knows she understood them correctly. Types of confirmation include Implicit confirmation and Explicit confirmation. (Source: Alexa glossary)

Conversation design, at its heart, is about teaching computers to communicate like humans, and not the other way around. It’s about making these experiences easy and intuitive, and reducing frustration. At a more practical level, it’s about designing experiences that include conversational interactions, whether that’s through a voice user interface, a voice-forward screen, or a multi-modal device like a mobile phone that may include typing, tapping and swiping.

Also known as VUI designers or conversational user interface designers, these individuals are responsible for designing and building out voice user interfaces and making conversations between humans and computers as seamless as possible. The discipline as a whole is made up of several design disciplines including voice user interface design, interaction design, visual design, motion design, audio design and copywriting. The goal of the conversation designer is like that of an architect, mapping out what users can do in a space, while considering both the user’s needs and the technological constraints. They curate the conversation, defining the flow and its underlying logic in a detailed design specification that represents the complete user experience. They partner with stakeholders and developers to iterate on the designs and bring the experience to life (source: Actions on Google) 

Refers to the use of messaging apps, speech-based assistants (Amazon Alexa, Google Assistant etc.) and chatbots to automate communication using Natural Language Processing and enhanced machine learning through a spoken or typed interface which creates personalized experiences at scale.

A conversational user interface are platforms that house artificial intelligence-supported voice apps, chatbots and IVRs to have verbal or written interactions with human users. The goal of CUIs? To mimic human conversation.

A Voiceflow project type that allows you to design, prototype, and export your experience to any conversational channel or assistant.

When something unexpected happened in the conversation between Alexa and the customer. Types of dialogue errors include low confidence errors, timeouts/silence/no input, and false accepts.

A design system that offers a more flexible way to design customer-centric voice experiences. This system involves writing more scripted dialogue between the voice assistant (Ex. Alexa) and the customer so that you can take those conversations and convert them into storyboards.

Dialogflow is a conversational platform that lets developers design and build Google Actions, chatbots, and conversational IVRs. Voiceflow allows your to import your projects to Dialogflow, where you can publish your Actions to Google Assistant. Unlike Voiceflow, coding is required.

The message delivered to a customer when an utterance or technical error occurs during a dialog. (Source: Alexa glossary)

When the customer says a command like exit or stop to end the interaction.

A prompt that repeats back what Alexa heard and explicitly asks the customer to confirm whether they were correct. For example, "Alexa, ask Astrology Daily for my horoscope". Alexa would respond with, "You wanted a horoscope from Astrology Daily, right?" (Source: Alexa glossary)

When Alexa has mid to high confidence that she correctly understood what the customer said, but she actually misunderstood.

Skills that have been built specifically for Amazon Alexa's 'Flash Briefing' feature, which provides users with news headlines and updates, event information, local weather reports and other forms of short-form content.

A service, app, feed, conversation, or other logic that handles an intent and carries out the corresponding Action.

A set of actions or tasks that are accomplished by Google's voice assistant.

A developer tool that lets you create, maintain, test and publish Actions.

A program interface that uses a computer's graphic capabilities to make it easier to use. GUIs make it possible for users to interact with electronic devices (computers, phones, gaming devices, etc.) through visuals like graphical icons. It is occasionally referred to as "gu-ee".

A happy path is a streamlined path of execution - like in a voice app for example - which features a default progression of events where no exceptional or error conditions arise. This is ideal when building the simplest flow of logic through a system or task. Where the "happy path" falls short is identifying and planning for unexpected inquiries that land outside of the default progression of the event or task.

The physical hardware portion of a platform, such as your physical iPhone. It is a shell that is useless without software giving it instructions for what to do.

A prompt that subtly repeats back what Alexa heard to give the customer assurance that they were correctly understood. In the following example, repeating back the word horoscope is a landmarking technique used to establish trust with the customer but still supports natural dialog. For example, "Alexa, ask Astrology Daily for my horoscope". Alexa would then ask to clarify the request with, "Horoscope for what sign?" (Source: Alexa glossary)

With in-skill purchasing (ISP) for Alexa skills, you can make money through your skills by selling digital products to customers.

When building Google actions, this refers to a feature that lets you assign different weights to intents for matching. If a user query can be matched to multiple intents, Dialogflow (Google's natural language understanding platform) is more likely to trigger an intent if it has a higher priority. (Source: Google design guidelines)

Tasks your assistant can do for you. Simply put, an intent is the user's intention in a given sentence or command. For example, if the user said "order me a large mocha coffee" the intent here would be to order coffee. An intent doesn't relate to the specific words "order" and "coffee" but rather the goal they are aiming for which is to order a coffee

Based upon the idea that a computer needs specific information to understand human language. The interaction model provides the necessary information for a computer to understand and process a given voice request or command. This incorporates the use of utterances, intents and slots which all map out a user's spoken input. (see these definitions for more info).

An automated phone system that provides pre-recorded voice responses that can interact with callers, gather information, provide information, and route calls to the appropriate recipients via voice or touchtones on a keypad device.

A device or program enabling a user to communicate with a computer.

The interconnection via the Internet of computing devices embedded in everyday objects, enabling them to send and receive data. Examples of objects that can fall into the scope of Internet of Things include connected security systems, thermostats, cars, electronic appliances, lights in household and commercial environments, alarm clocks, speaker systems, vending machines and more.

When creating a custom Alexa skill, you will need to provide an invocation name that users will say to open your skill. For example, you might say, "Alexa, play Game of Thrones Quiz". The invocation name here would be "Game of Thrones Quiz".

A JSON is a text-based data format which is inspired by Javascript. It is a type of 'code'  used to transmit data between a server and a web application. In Voiceflow, JSON lets you transfer data from your google sheets to your project.

When Alexa has low confidence that she correctly understood what the customer said. When this occurs, Alexa cannot proceed in the interaction without asking the question again or ending the interaction.