Apple AI Audiobook Narrators

 

Audiobooks are nerve-wracking to produce by yourself. Sure, you can offer a shared royalty route with the narrator and hope to find a good one. But a narrator search can be difficult, frustrating, and time-consuming. Not to mention, the entire production process is  daunting and expensive. Where to begin?

According to Apple, not with a human. Apple started production of digital audiobooks using artificial intelligence, specifically two AI narrators named Madison, a female soprano, and Jackson, a baritone. The platform uses advanced speech synthesis technology combined with input from linguists, quality control specialists, and audio engineers. Currently Madison and Jackson are used for fiction and romance only. In the near future, Apple will have two additional digital voices, Helena and Mitchell, for nonfiction and self-development audiobooks.

 If you’d like to hear a sample of Madison click here.

 According to Apple, these are the benefits:

·        The audiobooks will be easy to produce and delivered via preferred partners. The original ebook must be created in either Draft2Digital or Ingram CoreSource.

·        Audiobooks have wholesale price limits. (The website isn’t clear on what they’ll be.)

·        Distribution will be solely via Apple Books and to public/academic libraries.

·        Publisher/author retains audiobook rights, and there are no restrictions on producing and distributing other versions of the audiobook.

How do you make an Apple audiobook?

The ebook must be created with either Draft2Digital or Ingram CoreSouce. Then the author selects the title. Apple has a review process and acceptance isn’t guaranteed. The general requirements are as follows:

·        Ebook must be available on Apple Books.

·        Author must own the audio production rights.

·        Primary category must be romance or fiction. The only subcategories currently accepted are literary, historical, or women’s fiction.

·        Book must be in English.

How good are AI narrators?

Frankly, Madison is fine. A lousy narrator can ruin a good audiobook and I stop listening when any set my teeth on edge. Madison has a pleasant voice with good tone, if a trifle unemotional. If you listen to her, you understand why Apple limits the AI to audiobooks without an exciting chase scene or hilarious denouement. An AI can’t make handle extreme ranges of emotion. Other things AIs can’t do:

·        A multitude of characters in the same book. Their voice is typical of a national newscaster; nothing to determine a regional accents. Nor can an AI handle a stutter, quirky word pronunciations, foreign words and phrases, or fictional words. (Sorry, Samuel Clemens, J. R. R. Tolkien, and me. Our work doesn't qualify.)

·        Difference in ages. All the characters sound roughly the same age.

·        Difference in genders. Male and female characters speak with a similar tone.

 So what’s the big problem with AI?

Even if an AI sounds okay, I have issues. A top-drawer narrator makes an audiobook memorable, and AI has a long way to go to reach that level. Audiobooks are also an art, and frankly, I’m not crazy about the idea of a soulless digital character taking a job from a human who spent years honing a craft. Not to mention, a human narrator adds emotional nuance to every page, something an AI can’t do. AI narrators are still few and far between and until I have no choice, I’ll opt for a human every time.

 

 

 

Audiobooks Part 3: The 15 Minute Check

Once you select a narrator and have an accepted offer, the real work begins. The author sends the narrator the complete book manuscript, otherwise known as the script. I used the final Word version of the ebook minus the front and back matter. If you wish to make certain edits, do them before hitting Send.

The first file you receive from the narrator is the 15 minute check. When will you get it? Well that depends. The deadline is something you and the narrator agreed upon in the offer. Make sure to give the narrator enough time to put together a stellar read. I decided on one week and my narrator had no problem with that. The phrase 15 minute check is actually a misnomer as the narrator begins at the first page of the book and stops at a logical point roughly fifteen minutes later. For many books, mine included, this is the first chapter. Mine took a little over sixteen minutes.

Make sure you and the narrator are on track with pacing and flow. If you think the reading is too fast or slow, or didn’t quite capture the mood of a scene, say so now. Is any part confusing? If you have a dialog between two or more characters can you tell which one is speaking. Is the tone correct? Did a character who's supposed to be lightly teasing sound snarky and sarcastic instead? A few missed words in the script is no biggie. Simply note them down and the narrator can make corrections in the audio file. You’re not Steven Spielberg, so don’t pick apart each sentence. Remember, an audiobook is a collaborative process between two professionals. You want the narrator to bring his or her interpretation to your words. That’s why you hired a pro. But if a scene doesn’t work for you, state the reason clearly. Telling a narrator, “I need you to make this, you know, like better, you know, cause it’s like, you know, not right.” isn’t helpful. 

Next up in Part 4: Building the Book

Audiobooks Part 2: Egad! I Have a Narrator.

Egad, I Have a Narrator. Now What?

I posted the audition to ACX. The first response came that evening and then one or two a day; some were okay, some were, let’s just say, not so okay. I even got a message from a woman who wanted to submit an audition, but had to finish another audiobook and wouldn’t be available for a few weeks. That cheered me. If she already worked on an audiobook, she couldn’t be awful. She wanted to know when the audition closed. Hmm. Hadn’t thought about that. I figured this would be a long process, so I said July 15. I looked for a way on ACX to post the audition date. Couldn’t find one. Stupid ACX.

Narrations continued to arrive. None of them grabbed me, but I was too unsure to hit the delete button. As I listened to more, the okay ones started to sound the same as if the narrators practiced together; the same tones, the same inflection, the same reading. I began to worry. Maybe the okay auditions were really great, but I couldn’t feel it because I wanted the impossible. When I write, the characters speak in my head as clearly as if they were real people. (Sometime clearer, but let’s not get into my mental health issues.) How can I expect anyone to capture what’s inside me?

Then I discovered a wonderful truth. I can’t, but the right narrator doesn’t need my voice. She has one of her own and can add something different, but equally good, to a book.  Less than a week after posting the audition I found Cass, a professional voice actor in California. Her reading was so far above the others, I had no doubt she was the one.

Next came the hard part. I had to reject the other narrators. Writers get plenty of rejections. If I printed out all the ones I received over the years I’d be able to wallpaper every room in my house with enough left over to whip up stylish curtains for the windows. It hurts a little less with a polite rejection because you can delude yourself someone actually read the submission. The worst is the black hole. You slave over a proposal or submission, email it, and then…nothing. The agent or publisher is too busy sipping their lattes to send a canned rejection. They don’t even bother to assign it to the unpaid intern. He’s busy polishing their shoes and wondering if it’s too late to apply for that salesclerk job at Old Navy. I’m sure actors get as many rejections as writers, so I determined all who submitted an audition would get an easy let-down with a kind, but encouraging email from me.

But first, the offer. If Cass didn’t accept, I was back to square one. I sent a message through ACX and told her how much I enjoyed the audition and an offer was coming. I also mentioned terms were negotiable, since I didn’t want a rejection over a minor issue. She was thrilled. I sent it through the ACX site; flat fee, but was fine with split royalties if she wanted to go that route. I also listed the deadline for the first fifteen minutes (the first chapter check), and then the final deadline.  She accepted immediately, no changes necessary. Whoo-hoo! I went back to the list of auditions to start the polite rejections.

Curse you, ACX!

As soon as an offer is accepted the site deletes the contact information for other auditioners. Nothing warned me ahead of time. My stomach hurt thinking about those poor people waiting in the black hole. Will ACX notify them I chose another? Will they do it kindly?

Note to narrators who auditioned for Rimrider:  Please don’t hate me. I intended to send a heartfelt message of thanks. Don’t let my rejection discourage you. Just because your narration style didn’t suit me, doesn’t mean it won’t suit another.

Fortunately, ACX only deleted those who actually auditioned, so I was still able to send a message to the nice woman who wanted to know the deadline. I explained that I expected to keep auditions opened to the 15th, but found a narrator right away. I wished her luck in future endeavors. She sent me a thank-you note.

Lessons Learned

• The narrator doesn’t need to copy the author's idea of a character’s voice. A talented narrator will bring her own skill and interpretation and an author may even like her interpretation better. Shut up, voices in my head.

• ACX needs work. Amazon owns the world. Can’t they spend a few extra bucks to hire some techs to get the bugs out of the system and make the site easier to use?

• Offer a narrator both flat fee and split royalty for payment, but be prepared to pay. Voice actors like to eat, too, and I believe most want money up front. If I only offered split royalty, I’d still be waiting for a narrator.  

Next up in Part 3: The 15 minute Narration Check.

I've Jumped off the Deep End of Audiobooks and Feel Like I'm Drowning

After hemming and hawing, I’ve taken the first plunge into audiobooks. My publisher will begin to offer audiobooks within the next six months or so, but I decided to start with Rimrider, my self-published YA space opera series, to test the waters and get a feel for the process. I read all the articles I can, but still have no clue what I’m doing. I suspect they were written by people much smarter than me.

I chose ACX since it’s owned by Amazon and is the big dog on campus for audiobooks. They brag on the website that the process is painless. That’s not exactly true, especially for dummies like me who, as I said, haven’t a clue. The pages are set up weird and it’s hard to find specific information. After creating the account and claiming the audio rights for Rimrider, I wrote a short audition script. One section of the ACX website says it should be 1 or 2 pages; another says 2 or 3. I did 2-1/2 and hoped no one got mad. I used different passages in the book to get a feel for the actor’s emotional range. I didn’t find any way on the site to set a time limit to hold an audition. I decided to worry about it later and posted the call.

The producer (in this case, me) can put numerous qualifiers on the audition reading, such as tone, range, or emotion (you can ask for flirty, sheepish, and what the hell is a hip voice?)  My book has characters of different ages and scenes that require a range of emotion, so I only put that I wanted a female voice because it’s a teenage girl’s story. I listed the genre as science fiction/fantasy and posted payment information. I also added more details about the book, characters, (ACX adds your Amazon book description) and what I want for overall tone. My audition pages include a pronunciation guide for the characters and several short phrases that occur in Spanish so I know they’re said correctly. I have no idea how to set qualifiers to find the right narrator, but simply throwing my book up there and crossing my fingers the right person will magically appear seems like a terrible idea. I feel like I’m doing everything wrong.

What are my biggest fears right now?

• No narrator will want to do my book.

• Narrators will want my book, but no one’s voice will be right to bring the story to life.

• I’m doing everything wrong.

I'll post updates as I continue my quest to create a audiobook.