Based on Chuck Litka’s post Adventures in Audiobooks, I decided to go with Google’s audiobook option only. So this post refers exclusively to auto-narrated audiobooks on the Google Play platform.
I have finished setting up and editing one audiobook, which is now live. From that experience, I can make the following observations.
Once you have an ebook live on Google Play Books, it’s surprisingly easy to create an audiobook. That said, I fumbled my way through the process, and my first book went live in an unedited state. I will have to figure out how to keep that from happening with any others I publish, because it is absolutely necessary to listen to the entire book before finalizing it. There are step-by-step instructions in something called the Auto-Narrated Audiobooks Learning Center, but when I started the process, I found myself being hustled through a number of steps without really knowing what was happening. No harm done, however, as far as I know.
On the plus side, once the audiobook was live, it was easy to whip it into shape. I called up the Audiobook Text, which allowed me to both listen to and see the text. I could start and stop playback, make changes in the text, and save them. It’s possible to have more than one version of an audiobook (with different narrator voices, for example), but only one can be live.
There is a large number and variety of narrator voices available, including male and female voices in different age ranges (18-30, 31-45, 45-60, and 60+) with “standard” American, British, or Australian accents. Voices for a few languages other than English are available, but it’s recommended to use these only for texts in those languages. There are no options for English spoken with accents other than those I’ve already mentioned, or with regional accents.
It’s possible to use more than one voice in a book! Theoretically, you could have dialogue in as many voices as you have characters, but I think this would complicate the setup process. So far, I’ve used only one main voice, with a second one to read brief quotations that open a few chapters in my book.
Changes made to the audiobook text are not reflected in the ebook version. One hazard here is I was sorely tempted to improve the text! I don’t know how many instances of the word “that” I was tempted to delete, but I decided to make no changes except those needed to improve or correct the speech. I want the audiobook, ebook, and paperback versions to be essentially the same, stylistic problems and all. However, I did find it helpful to add or delete commas on occasion.
The computer-generated voices sound human, much more so than the rather robotic voice of Word’s text-to-speech feature. Nevertheless, they can’t be expected to represent the full range of emotion that may be found in a work of fiction. Google’s info about auto-narrated audiobooks cautions that they work best for texts that do not require a lot of drama and emotion. Still, I found the voices I selected to be better than adequate. Quite often, the main narrator was spot-on, to the point he seemed to embody the first person narrator of the book.
Quirks and Issues
- Stress and emphasis does not always fall where it should in a sentence. This can’t be changed by adjusting the speed of the narration, but deleting or adding commas helps sometimes. Still, I admit there are occasions when a word or sentence sounds a little “off.”
- Sometimes there is an awkward pause between a word or sentence spoken by a character and the dialogue tag such as “he said” or “I asked.” The best solution might be to delete selected dialogue tags, but I resisted the temptation to do this, not wanting my spoken and written texts to diverge. But this is another reason to use fewer dialogue tags!
- Weirdly, a few names are pronounced quite differently when a possessive is added. For one name, I had to provide a correct pronunciation for possessives because the default was unacceptable.
- Homographs are common enough that you have listen for instances where the wrong pronunciation pops up. For example, the default pronunciation of the word “read” is the present tense (pronounced “reed”). When the past tense pronunciation (“red”) was needed, I had to intervene. Fortunately it’s easy to fix these; a right click on the word in the text takes you to both versions, and you can listen to them before selecting the correct one. There is an option to change the pronunciation of all instances of a word, or only one.
- Abbreviations such as Mr. and Dr. are usually pronounced correctly, but I encountered a few situations where “Dr.” came out as “drive,” for some reason. I fixed these by spelling out the word.
- Uncommon words, place names, or words in other languages may be mispronounced. In such cases, you can insert a different pronunciation by spelling the word differently, speaking it into your computer’s mic, or by using the International Phonetic Alphabet. I actually did that for a few place names; fortunately Wikipedia sometimes provides IPA spellings in its articles, so I was able to reproduce them with good results. You can listen to the new pronunciation before selecting it. This was about the most challenging part of the editing process.
So what do I think of Google’s Auto-Narrated Audiobooks?
I think it’s an excellent option for authors who would not otherwise consider producing audiobook versions of their books. It doesn’t cost anything and produces acceptable results.
There’s no doubt that a competent human reader or voice actor would produce a superior listening experience, but at a cost that’s likely prohibitive for most indie authors. Some may have the talents and equipment to be their own reader, but I suspect those are a minority. The AI-narrated option is available for free to anyone.
A few more considerations:
- You have to publish your books as ebooks on Google Play before you can create audiobooks. Google requires book files in ePub, not Word. I used Calibre (a free program) to convert a copy of the Word doc I used for the Amazon Kindle version of my book into an ePub, which I then uploaded to Google Play Books. It helped that the Word doc was properly formatted and had a linked table of contents.
- You need a square cover image for the audiobook, but it looks like the rectangular ebook cover image is squared up automatically with a block of matching colour, so you can get away with that.
- You need to commit the time needed to listen to your audiobook from start to finish in order to correct any serious or even mildly annoying problems in the finished product. The book I worked with is a fairly hefty tome, which ended up being more than 15 hours of listening time. It took me a solid week to complete, spending 2 to 3 hours each day. (Actually, this reminded me why I prefer reading fiction rather than listening to it.)
I encourage anyone who wants to offer their books in audio format to give this a try. The only cost is your time.
Once I’ve converted one more book to auto-narrated audio format I will write a post on my own blog with more details. That should appear in another week or two.
Featured image from Pexels
Writers Supporting Writers 
I am very impressed Audrey that you are giving this a go. I can’t imagine myself doing this, but then I thought downloading a book on Amazon was as likely as going to the moon when I first started writing! I would still prefer to hear a human being of mellifluous voice reading to me. Audio books are popular, though I don’t choose them as there is plenty to listen to on the radio. Which age, sex and accent did you choose for the voice?
LikeLiked by 1 person
I was convinced by a fellow writer’s account of working with ai audio, so gave it a try.
I picked a middle aged American male voice for the first book. Very sincere sounding. The older Brit who reads the quotations at the beginning of some chapters sounds serious and scholarly. The second book has a young American female voice; I’m trying to decide if I like her. I might try a different one, but I’ve just started working with it.
LikeLiked by 2 people
Thanks for this, Audrey. I still need to get my books on Google Play. This provides some incentive for doing so.
LikeLiked by 1 person
You’re welcome, Mark. It’s worth the effort.
LikeLike
Wow. You really put the time and work into the project. I am very impressed, and semi-embarrassed that I don’t. Perhaps I trust the machine too much. I just checked the pronunciation of my made-up words. Alas, good enough is my default standard.
Keeping the audiobook faithful to the print version is an interesting issue. I know that some people read along in the book while listening to the audiobook, so making changes might be disconcerting to those readers. On the other hand, the options Google offers, different voices, at different speeds for different characters, would allow an author, with the right type of story, to craft something of a radio drama out of the book – distinct voices for the characters would allow for the dropping of a lot of dialog tags (but probably not all) making it more like a script for a play. I know some audio books are produced more like plays, with sound effects as well as multiple voice actors for the different characters. You could be one of the cool kids. Sort of.
And the reverse is also true. I listened to a scene early in one of my books were two people are conversing without dialog tags. It works in print because the structure of the words on the page make it clear who’s saying what. However, in the audiobook version, without that visual structure, the back and forth of the dialog became less clear who’s saying what. I didn’t, but maybe should, add dialog tags to the audio version to avoid this confusion.
My problem is that I really don’t like audiobooks, and have only sampled a few, so I have no basis for judging the quality of these auto-generated narration. That, and the fact that I can’t read, much less listen to my work, without wanting to change it. For me there is no right word, just the write word for the day.
Anyways, I hope this brings you new fans. It may take awhile. I think I had my ebooks on Google for two years before they started getting traction. But it’s a market of a billion devices, and a lot of people read – or listen to – books on their phones. I don’t think its a market that indie authors should overlook.
LikeLiked by 3 people
Thanks, Chuck. I’m glad you brought up the point that some people read along with the audiobook, so keeping them the same makes sense.
Really, this opens up a whole new type of work for indies. You’re right, we could go into full production mode and turn our books (some of them anyway) into plays, with different voices. I wouldn’t be surprised if Google or someone else begins to offer a much wider range of voices to work with, as well as sound effects and music. Probably for a fee. Sort of the way Canva offers effects and image elements, either individually or as part of a paid subscription.
For the present, I think I’ll stick to my texts, despite their imperfections. 🙂
And like you, my experience of audiobooks is limited. I listen to radio a lot, and have to make myself not do things like reading or even writing blog posts at the same time, if I want to absorb what is being said. Listening to something while doing manual tasks that don’t take up much brain power (washing dishes, vacuuming, etc.) is the ideal combination. And a perfect accompaniment to long drives, of course.
LikeLiked by 1 person
Thank you for this detailed information about creating audiobooks on Google Play.
LikeLiked by 1 person
You’re welcome, Liz.
LikeLiked by 1 person
Bravo, Audrey. I’m impressed by your expanding computer & AI skills.
But, why this archaic adherence to spoke == text? Why not allow them to drift? Who’s gonna catch the difference? And if you’ve spent all that time honing it, only to leave it still chipped, why bother at all?
Last night I started to listen to The Sun Also Rises – read by William Hurt. He’s got a great voice and doesn’t try to mimic a woman or child with dialog. He’ll intone such spoken words a bit different but that’s it. What struck me was there was not a “he said,” “she said,” in the recording. Stricken from the audio, the recitation flowed seamlessly.
I couldn’t listen to the story however, what utter drivel. Hemingway, shemingway. Blah blah blah, we drank wine, bullshitted about the Seine, the cafe’, the help, the petty relationships — and the passive text! Sheesh! Was, was, was. By chapter 4 I was skip, listen, nope, same shit. Skip, listen, nope, same…
LikeLiked by 1 person
You have a point about the audiobook as a separate work, rather than a rendition of a written one.
You had better avoid my book. Lots of “was” and dialogue tags there. In fact it sounds early 20th century.
LikeLike
Thank you for the comprehensive observations. By the end, you’d answered all my questions except the moral one: how do you feel taking a job from a human?
I am strongly against the use of AI for things that humans are doing, but I also have the view that it’s going to be the wave of the future, so those narrators will need to specialize or find another job. For me, the difference in cost between $0 and thousands is the difference between producing an audiobook and not. I must answer the question- how important is it for me to get my books out to a new group of listeners, as well as those who are sight-impaired?
A popular meme: “I want AI to do my laundry and dishes so I can do art and writing; not for AI to do my art and writing so I can do the laundry and dishes.”
LikeLiked by 2 people
It’s hard to argue with this, Mollie. But I’m not taking a job away from any human because for me the choice is between the AI narrator or none at all.
At the same time, I have no intention of using AI for writing. I’ve tried it twice and recognize that it can be useful for assembling facts into prose, thus a shortcut for factual type writing (except sometimes AIs make things up, let’s not forget). But for creative writing? Never.
I suspect that any AIs that could do housework would also be corporate spies in our homes. So no thanks to those too. 🙂
LikeLiked by 2 people
Very impressive and informative, Audrey. Thanks for the review.
LikeLike
You’re welcome, and thanks!
LikeLike
Very good update and review, Audrey. Thanks for sharing this.
LikeLiked by 1 person
Thanks, Pat, and you’re welcome!
LikeLike
Great information, Audrey. I didn’t realize it was free. Now to find some time to try this! 🙂
Thank you for your great blogs!
LikeLiked by 1 person
It’s free so far; I’m not sure what the Google gang have in mind for this service.
LikeLike
And you’re welcome! 🙂
LikeLike
Hi Audrey, this is very encouraging. I’m currently using Alexa to read certain ebooks to me.
LikeLiked by 1 person
I’m not familiar with Alexa so don’t know how she compares to the Google voices. I am quite pleased with “Matt,” the voice I selected for my book.
LikeLike
Alexa isn’t great, but she gets the job done. I use her for books where there is no audiobook alternative.
LikeLiked by 1 person
Brave of you! No matter what you do with this way of making audiobooks, someone will be unhappy, so just don’t let it be you.
I WILL – God willin’ and the crick (creek) don’t rise – do the ‘as read by author’ (not ‘as PERFORMED by author) version of the Pride’s Children trilogy when LIMBO is finished. But no idea when that will be, and meanwhile I am not spending an instant that could be used to write on this, so thanks for your comprehensive review of doing it successfully.
LikeLiked by 1 person
Thanks, Alicia!
At times I’ve contemplated making recordings of myself reading my books, but I’m too lazy to assemble the right microphone and recording space, never mind figuring how to work with sound files. When I became aware of the Google Play option, I was motivated to try it.
LikeLike
It’s brilliant – for some things. And it may turn out, in the long run, that it would have been good to have that option executed, because I never got to the one I really wanted, which is doing it myself.
And then I told myself to stop worrying – there are more important things in life, and I think there are options for people to have an ebook read to them by a voice on their own computer/phone, if they’re in that much of a hurry AND need the audio version.
I am severely limited in what I can do – my decisions won’t always be right, even for me – and stressing about any of that steals energy.
But if I read, I will be doing it ONCE, my way – when I can. After all, we don’t have Charles Dickens reading us Great Expectations, and we’ve survived.
Good luck with your chosen path – I’d love to hear if it improves sales (the great perennial question) for YOU.
LikeLiked by 1 person
I do like the idea of reading my book to blog followers in 15-minute segments, with a complete audiobook as a by-product, but I think I’ll settle for the auto-narrated option right now.
I do intend to post about how things work out.
LikeLiked by 1 person
Go for it, of course. When you have control like that, because you’re posting on your own blog, you can re-do earlier episodes if you like how you’re doing the later ones better, or add a disclaimer, or take the whole thing down…
LikeLiked by 1 person
I’m paying for my WordPress blog now – the ads were getting ugly – I’ll have to check if I’m now allowed to post audio or video. It’s not available in the free blogs, probably because it takes a lot of storage space.
LikeLiked by 1 person
I recorded myself reading part of a story on Zoom, put it on YouTube and linked to that from my blog. I think that’s about as basic as you can get, and I can’t see myself doing any more of it.
A good microphone and some sort of recording space would produce better results, but as you say, one would then have to figure out how to deliver them to blog followers.
LikeLike
Cool! Audiobooks have standards for noise and such, but doing it your way doesn’t meet those standards, and you’re not claiming it does. I’d say there’s still some charm for those who want to listen to how you, the author, read it.
And they’ll be okay with any flaws, because you aren’t trying to meet those standards.
LikeLiked by 1 person
Very informative and thank you Audrey.
A couple of notes…
First the trivial one:
If you go the Audible route (using ACX where you audition people for recording), you also need a square graphic for your book. If anyone is interested in my experience with ACX, I can write about it.
Now the not-so-trivial one:
Does Google site the source for their voices? If it’s completely machine-generated, I’m okay with that. If it’s AI, then I would want to know if only paid voice actors were used for AI learning. You may have seen a recent lawsuit involving a ChatGPT voice app and 3 celebrities they stole samples from.
The AI community seems to strongly prefer pirating and stealing over paying artists, as if they’re entitled to anything because it’s out there (note how jealously many of them guard their own IP). I’ve had arguments with a few supporters about that point. My final responses to them is, if you have to dice the law – which in the past supported things like slavery and land encroachment over natives – rather than simply legitimately hire someone like many companies have pre-AI. It’s not that expensive for a company to do so. Remember the TIme Lady at AT&T. As it stands, If there is a choice, I won’t use AI unless the company has a clear statement that training sources were taken from paid artists who were aware of the potential use of their creative output.
LikeLiked by 1 person
Wish I could edit lol.
If you have to dice the law, etc… then you know in your gut you’re defending an immoral choice.
LikeLiked by 1 person
I looked at the FAQs about these audiobooks provided by Google. No mention of how the voices are generated. Further checks on artificial voices indicate they come from processing masses of recorded voices. I suspect no individual credit or compensation, just like the data for ChatGPT. So whether to use these voices is a decision we all have to make, as with AI applications for creating images or text.
LikeLike
I think we probably know the answer since they don’t provide one. Sorry to get on my high (hAI?) horse about it, but it’s one of my buttons. 😉
LikeLiked by 1 person
You’re not alone, Richard!
LikeLiked by 1 person
I admit I don’t know how the voices are created. I will have to look into it. I did hear about at least one celebrity who has filed a lawsuit over the issue. I’ve also heard that any and all written material on the internet has been scraped for AI training purposes, including our books.
LikeLiked by 1 person
I know it would probably be impractical and time consuming, but is there an option for an author to read his/her own words? I suppose one might also need speicqalized equipment as far as the sound quality.
LikeLiked by 1 person
Yes, some people do read their own works, but they need better microphones than the ones that come with laptops, and some sort of enclosed and padded space to work in. Then there’s the matter of working with the files. The Google option makes that equipment and skills unnecessary, which is why I was tempted to try it. And not everyone reads well, even stuff they’ve written.
LikeLiked by 1 person
*specialized
LikeLike
Really interesting to read of your experience. Thanks for posting about it! The Google tool sounds helpful in allowing you to review the audio and fix the instances where — as you described — “read” should be pronounced differently. And for us indie authors, the price is right. Instead of shelling out money, it sounds to be a time and effort commitment for reviewing the audio. I hope your audiobook reaches new readers (er, listeners) for your books!
LikeLiked by 1 person
Thanks, Dave. I hope so too.
LikeLiked by 1 person
Fabulous post, Audrey. I’m bookmarking it for future reference. I’ve never even thought of publishing to Google Play Books or whatever it’s called, but epub is fine as Storybox uses epub by default. Definitely going to give this a try. 🙂
LikeLiked by 1 person
Thanks, Meeka. Good to hear I inspired you! I’ll be posting some more on my blog about this audiobook project in the near future.
LikeLiked by 1 person
Looking forward to it. This is one use of AI that’s a positive, although maybe not for those who make a living from voice overs. Then again, they will remain the gold standard so perhaps not all negative.
LikeLiked by 1 person
Good, fast, cheap–pick two!
It’s unlikely that indie authors with limited budgets would ever hire a professional voice actor. They just wouldn’t go into audiobooks at all. Recording oneself would be another option, of course, but that’s not for everyone either.
LikeLiked by 1 person
That’s very true. Indies are DIY by definition. I do wonder about the publishing houses though.
LikeLiked by 1 person
I’ll bet they use AI!
LikeLiked by 1 person
Yup, especially for covers in genres that are, um, rather formulaic. 😉
LikeLiked by 1 person
Torso books, maybe? 😀
LikeLiked by 1 person
-cough- yes, rippling torsos… -cough-
LikeLike
Those are the ones! 😆
LikeLiked by 1 person
This sounds very similar to the Amazon process that’s being beta tested now. And I agree that there’s a huge temptation to edit the audio book text (I felt it) and had to stop myself. Keeping the audiobook and ebook text the same seems important. Thanks for the overview, Audrey.
LikeLiked by 1 person
You’re welcome, Diana. Amazon audiobooks as yet aren’t an option in Canada (except for Audible).
LikeLiked by 1 person
I figured that. It’s probably coming, but at least you have a very similar option.
LikeLiked by 1 person