It’s Never too Early to Get Started with Voice Tech
Twelve-year-old Aariv Modi is taking the voice community by storm as a young but brilliant developer. When he’s not playing chess, basketball, or reading books, Modi creates Alexa skills and speaks at voice tech industry conferences globally. In fact, Aariv was among the most anticipated speakers at last year’s Voice Summit and was named 2020’s “Voice/AI Industry Pioneer of the Year.” You must be wondering, if a seventh-grader can make a voice application, can I do it too? How difficult can it be really or is this a kid genius?
Getting Started - Voice Tech Application Tools
There are numerous tools available to create voice applications on two of the most widely used voice technology devices, Google Assistant and Amazon Alexa. Luckily, creating voice applications is a fairly straightforward process.
As with all Google products, the voice tech leader would like Google Assistant users to enjoy its wide array of conversational actions, but to also make it easy for anyone to build experiences that will benefit the user and the whole community. See a need, meet a need. As humans, we seek to capture and transmit our voices to communicate with others in a meaningful way, and voice technology is here to assist.
You’re going to want to start in Action Console, where it will ask you what kind of Action you want to build: Smart Home, Game, or Custom. You can start from a blank project or go off of one of the preset templates for actions. Luckily, the step by step process is pretty self-explanatory.
Of course, you could always partner with platforms like VoiceFlow to design, prototype, and build your voice apps collaboratively. No coding is needed as you try different ways to get the user experience right before building yourself. With a familiar product design, you can approach voice with more confidence and ease. At this point, they are powering 250 million conversations a year on Alexa and Google Assistant alike. (You will want to stick with one platform throughout the whole process, as it can get confusing when agent configurations and codes are hosted separately.) Nowadays, these platforms are creating dual functionality so that you don’t have to create two separate apps for Alexa Skills or Google Actions.
To make your Alexa skills more engaging, Aariv recommends using Speech Synthesis Markup Language. You can use SSML in your output speech response to control how Alexa generates the speech. For example, you can add pauses and other speech effects. He goes on to encourage speech cons, Polly voices, sound effects, and APL to increase engagement. To improve retention, Aariv recommends minimal friction, high-quality content, triggers, personalization, and feedback.
To get more updates and information on the latest tools for developers as they create new and innovative content, please subscribe to the monthly industry show, VOICE Talks. Also, grab your seat now for VOICE Global 2021, June 16, a 24-hour inside look at how brands around the world are incorporating voice into their businesses being held live across 120 countries. Who knows, maybe you’ll be named the industry’s next pioneer?