Tell Me A Story, Robot
“Make it a story of great distances and starlight…”– Robert Penn Warren from Tell Me A Story
[Update: In the last nine months since I posted this article, several exciting new advances in Text-to-Speech technology have arrived on the scene. At the end of this article, I have included information and thoughts on two of these new developments that you can try out for yourself, for free, today. If you are a first-time reader. I’d encourage you to read this post from the beginning. If you prefer to listen to this full article as read by a robot, click here.]
This post has been the most popular read of the many fiction and non-fiction musings you can read on my blog. Why is that? I have two theories. First, it seems to have very good Google search placement. Although I published this article here nine months ago, Google Analytics tells me that new people are continuing to read it daily. One of the companies mentioned in the article below even contacted me for an interview regarding my research and writing about Audiobooks and Text-To-Speech. My second theory is that people love Audiobooks, podcasts, voice assistants and all the new ways we can listen to and tell stories. So they want to read all about it.
If you have previously read this article, you can skip to the Updates below.
If you’re reading this, then you’re a reader, That’s obvious, even tautological (nice word!). What I mean is that you’re most likely a lover of books and good stories. But when someone says, “Tell Me A Story,” they are not talking about reading and writing. They’re talking about speaking and listening. Telling stories out loud is more primal. It runs in our DNA, and it was really the way stories were enjoyed and passed down up until the time of the Bible and other foundational texts like the Iliad and Gilgamesh. Even then, very few people could afford those painstakingly handwritten manuscripts, so they recited them – enter the dawn of the audiobook. Read on and join me on a journey into Text-To-Speech(TTS) and the burgeoning tech effort to turn robots into storytellers.
As parents, we have dutifully passed down the telling or reading of stories to our kids at bedtime. The tales delight and calm them, planting the seeds of pleasant dreams. Maybe this explains the popularity of podcasts and audiobooks. We have a relatively new platform for the dissemination of the spoken word with the surprise and delight of stories well told.
I grew up addicted to the spoken story with Mystery Theater on the radio. My parents’ generation listened to shows like The Shadow and Our Miss Brooks. And almost everyone has heard the famous Orson Welles’ War of the Worlds. As an adult, my love of audiobooks dates back to Books on Tape that started up in the 1970s – BOT is still around. On my long work commutes, great stories whisked me away to distant places and triggered my imagination, shrinking my perceived commute time to nothing.
Audiobooks, Podcasts-Give Me More
Now that I am a writer, of course, I would make my novels into audiobooks – NOT SO DEAD audio appeared in early 2018 and NOT SO GONE earlier this year. That journey began with interviewing ten narrators/actors to do the fourteen different characters. Since by now my wife, Amy, and I listened to hundreds of audiobooks in the years since Books on Tape, we had a good ear for what makes a great narrator. You don’t want an overly dramatic narrator – that would take away from the story – but you do want an actor who knows when to speed up with the action and emphasize specific words. And you don’t need a man who can sound perfectly female when he is performing a woman’s part – only slight changes in pitch and cadence will do the trick. The narrator is really a midwife who helps readers give birth to their own personal experiences of the story.
Text-To-Speech-Is It Any Good?
With this in mind and being kind of a techy myself, I was intrigued when invited to beta test a voice synthesizing program from the well-funded tech startup WellSaid. Text-to-speech (TTS) is a rapidly-growing field of machine learning with many players from start-ups to the likes of Google, vying for the lion’s share of the projected $3 billion TTS market. Could TTS replace human narrators at much less cost? Would the quality be there?
WellSaid’s YouTube demo was impressive. So as a beta tester, I had the opportunity to try it myself. I inputted my text, selected from one of three digital narrators, and a human-like voice read it aloud. Here are the first few sentences of the first chapter of NOT SO DEAD done by the Voice Synthesizer – compare them to my human narrator, HERE. What do you think (please leave a comment below)? I also tried Google’s TTS which boasts of 100 voices to choose from in more than 20 languages. You can try your own Google TTS experiment for free here. My opinion: for a straight reading of the news or maybe even for advertising voice-overs, it’s fine. The words are pronounced correctly, but TTS has a way to go for storytelling. Human audiobook narrators are safe for now. Storytelling requires a great deal of nuance in the tone and emphasis to deliver an exceptional audio experience. And for the foreseeable future, that appears to be way beyond the current software wizardry.
In fact, it took decades beyond landing a man on the moon to reach 99% accuracy with Speech-To-Text (the flip-side of TTS) aka turning your voice dictation into the written word. The futurists had no idea that the task was more complex than a moonshot, but Speech-To-Text eventually got there. Take this a step further and maybe we writers and creators need to look over our shoulders as Artificial Intelligence can actually write and create fiction and do it well. So well, that when Open AI created a very powerful content creation program, it scared them and they shut it down. Similarly, who thought computers could beat the world’s top chess champion or the top Go master and they did. What does all this mean for our future? I’m not sure, but I will be watching and listening and still writing with anticipation. In the meantime, I don’t believe anything will replace Mom or Dad reading you Good Night Moon before bed anytime soon.
Update New Text-to-Speech Free Tools
Here are too pretty cool tools I have discovered since writing the above article. I actually use both of them every day. I’ll explain.
Balabolka. I recently finished writing my latest novel, NOT SO DONE, and I am finishing up my own editing pass before handing the manuscript off to my beta readers and a professional editor. One critical part of my editing process is to read each chapter aloud. Why? By reading the text aloud, I not only catch errors, but I can hear if the dialogue sounds natural and the story makes sense to the ear. When I wrote my first novel, NOT SO DEAD<link>, I read it aloud to myself. That worked OK, but it’s better if somebody else reads it to you, the distance and detachment really lets you listen. That’s where the app Balabolka really helps. I only learned about it last month, installed it on my PC. and it reads NOT SO DONE back to me, highlighting the text as it goes. The voice is a little robotic, but it’s certainly good enough for editing purposes. It has several cool extra features, including the ability to save what I’ve written to an MP3. I use the recording feature to create the audio version of this article. Not bad, right?
Google Read-It-To-Me. Did you ever find a fascinating long article on the web and think, I’ll read it later? Well, why not jump in the car and let Google read the article to you? You can do that now, at least on Android. If I’m using the Chrome Browser and I’ve teed up a great article, all I need to do is say, “OK, Google, read this to me.” And it does with a remarkably good female voice. It gets the pauses right, and she even seems to take breath from time-to-time. Try it for yourself. Does it work on an iPhone, I don’t know. Perhaps, if you download Google Assistant and Chrome apps, it will. If you do, please leave a comment and let us know.
Finally, try my updated comparison test of human verses artificial robotic narrators of the first chapter of my novel, NOT SO DEAD.
Synthesized Voice #1 from WellSaid Labs – Listen
Synthesized Voice #2 by Balabolka – Listen
Human Voice #3 by Daniel Greenberg – Listen
What do you think (please leave a comment below)?
Happy reading! Or should I say listening…
— END —
P.S. My original fast-paced thriller NOT SO DEAD and the new techno-thriller, NOT SO GONE, are now available on Amazon. Read more about it. Better yet, buy a copy
Audiobook versions available on Amazon, Audible and iTunes