← The Creative Penn Podcast For Writers
The Creative Penn Podcast For Writers
Producing AI-Narrated Audiobooks Using ElevenLabs With Simon Patrick
00:46:39
Is the high cost of audiobook production holding you back? What if you could create a high-quality audiobook for a fraction of the traditional cost? In this conversation, Simon Patrick explores the world of AI narration with ElevenLabs,
Loading summary
Transcript91 lines
- [00:01]
Joanna Penn
Welcome to the Creative Penn Podcast. I'm Joanna Penn, thriller author and creative entrepreneur, bringing you interviews, inspiration and information on writing, craft and creative business. You can find the episode show notes, your free author blueprint and lots more@thecreativepenn.com and that's Pen with a double n. And here's the show. Hello creatives, I'm Johanna Penn and this is episode number 816 of the podcast and it is Wednesday 25 June 2025. As I record this in today's In Betweenisode, I talk to Simon Patrick about AI audiobook narration. Using ElevenLabs, we discuss the costs versus the benefits of human versus AI narration ElevenLabs realistic and expressive voices, creative control and ownership of final audio files for distribution practical tips for AI narration, elevenlabs v3 and why emotion tags are so exciting Creating and monetizing a voice clone and publishing on 11 reader so you can check out elevenlabs at elevenlabs IO or I have an affiliate link@thecreativepen.com elevenlabs and you can use the number 11 or the text 11 so thecreativepenn.com today's show is sponsored by my community at patreon.com thecreativepen and thanks to everyone who's been supporting for months and years. If you join the community, you get access to all my backlist videos and audio covering topics on writing, craft and author business, as well as tutorials and demos on AI tools, including 11 labs. The Patreon is a monthly subscription, the equivalent of buying me a black coffee a month or a couple of coffees if you're feeling generous. So if you get value from the show and you want more, come on over and join us at patreon.com P-A-T-R-E-O-N.com TheCreativePenn Right, let's get into the interview. Simon Patrick founded 10 Times Better Books to support his daughter Abby Patrick. As one of elevenlab's first users and beta testers, he has produced several of their most popular AI voices. He now develops courses and AI audio book solutions for independent authors at Novel Productions. So welcome to the show, Simon.
- [02:37]
Simon Patrick
Thank you. Joe is such a joy to be speaking with you. Your podcast and books were foundational to my daughter Abby basically becoming an author and me learning to be her publisher and all that's happened since. And I love your patron. It's the best money I spend every month. Frankly, it's just a great community to be part of. So it's Such a joy to be sharing some of what I've learned.
- [02:54]
Joanna Penn
Oh, thank you so much. So, yes, behind the scenes on the Patreon, Simon has done a demo, a video demo of 11 labs. And today obviously we're doing audio only. But first up, tell us a bit more about your background and why you decided to get into AI narrated audiobooks.
- [03:11]
Simon Patrick
Okay, well, I've got 25 years experience in marketing and design. I still am half time head of communications for international charity. But we've always had our own businesses too. My wife and I ran a small home education tuition publishing business. We've home educated our three kids. Which brings me to Abby, who's my daughter who brought me into your world. Jo Book publishing. She was going to college. She was studying early as education and just was bored out of her mind. She asked if she could drop out of college to be a writer instead. She'd been writing a book since she was 15, and to the astonishment of her friends, and some of ours too, we said yes. Let me add, it was responsible parenting. We made her finish the term, stick it out, do the work experience. But by Christmas 2019, she'd left to pursue finishing her book based on the deal that if she'd learned to write, I would learn to publish them for her.
- [04:02]
Joanna Penn
Wow.
- [04:03]
Simon Patrick
Yeah. So I attended the first self publishing show in that crazy spring 2020. I think you were there too.
- [04:09]
Joanna Penn
As I was before the pandemic shut down.
- [04:12]
Simon Patrick
A few days before the pandemic. And yeah, I've listened to hundreds of your podcasts, read your books, done some of the self publishing formula courses and learned to be Abby's publisher. Really? And since then have used those skills connected with a few other authors. So I probably publish a book a month or two, something like that. But audio has always been the stumbling block. I love audiobooks. We as a family must consume hundreds of hours a month of them as incredible narrators like Ray Porter and Daniel Rigby, who self directs his own Audible exclusives, and my absolute favorite guy called Jeff Hayes, who narrates incredibly like they are amazing talents and I don't think AI is going to touch on them because they bring so much humanity to the performance. But to ordinary authors and publishers, those narrators are inaccessible. I don't even want to think about what they cost. And for Abby, who was, you know, she's still just starting out, really, any professional narration would cost her for her books, three to $4,000. It's just the maths don't work. And while there's options like Royalty split with acx, Audible's publishing platform. I struggle with that, I think, firstly, you're tied in exclusively to Audible for seven years and we're big fans of going wide, and you're only getting 20% of the royalties when it's being SPL. I just don't think for us they're ever going to make that money back. So all of that is what led me in early 2023 to be searching for AI audio options. ChatGPT was going crazy. You were demoing all of that at the time. And I figured there just must be some kind of AI audio option that would take control of the process, hopefully produce good audiobooks way more cheaply than the current options. And that's when I discovered elevenlabs.
- [05:54]
Joanna Penn
Yeah, well, lots to unpack there. First of all, I think, as you mentioned, there are some incredible human narrators. We want to acknowledge them. I'm also a human narrator myself, obviously, but as you said, for most authors, especially indie authors or new authors, it's not human or AI, it's. It's AI or nothing because they can't afford the fees. And as you said, a lot of the time you don't know if you're going to make the money back. So I think that's really important to acknowledge. And then, yes, there are lots of AI options. Obviously there weren't so many a few years ago, but realistically, there are so many. People email me all the time and say, oh, what about this platform? What about that platform? So it is hard for authors to decide which platform to use. So what is elevenlabs and why do you think it's the best option for quality and also for publishing reach? Because you mentioned ACX there, and there's obviously avv, the audible virtual voice. I mean, most people think, well, maybe I should just do that. So give us a bit of an overview and why you made that decision to go in for 11 Labs.
- [06:58]
Simon Patrick
Absolutely. So, yeah, 11 Labs continues to be the most realistic AI platform out there. They kicked off, like I said, two and a half years ago. I was one of their first users. And even back then they were so much better than everything else. There were lots of programmers and stuff wanting to do clever things with APIs and websites and stuff, but I was just like, I just want to make audiobooks with these things. And they were actually listening, which is remarkable in the publishing industry sometimes. You know, there's lots of things you can do with that technology. You can drop videos in and have it, translate it. You can have conversations with it but about a year and a half ago, and we're June 2025 right now for reference, they launched ElevenLabs Studio and it can take a whole book, like the EPUB that I've worked on for Abby, a Word document. You can drop it in and have it convert it chapter by chapter, paragraph by paragraph, into a great sounding audiobook. And like the high quality and natural sounding elements of it are why I first was attracted to them. The expressiveness, it's. It's just another step above. And we'll talk about what's happening right now with them in a bit. But the comparison with, with Amazon Virtual Voice, it's so much more pleasant to listen to, but it doesn't just sound better. What I love about it is the complete creative control it gives me. So there's thousands of voices I can pick from a whole library of voices. And they're real people. They're people like me actually, who's recorded their voice and licensed it to ElevenLabs and get paid a small, small amount. But when it's used, there's actually compensation to those who've licensed their voices to it. So it's not like the large language models like ChatGPT where the whole universe seems to have been scraped and just compiled into this thing. They're being super diligent about making sure it's all kosher, that it's real people's voices, that they're getting compensated. And in beyond that, the control, the tools they're building, they're incredibly open to listening to feedback, which has been brilliant. I'm talking to the programmers regularly. They've got a great discord where they're asking for feedback, but I can with the tools, just spend the time perfecting the book. I can get the dialogue just the way I want it. I can create a duet audiobook with male narrator for point of view POVs and female for female POVs. I can even do multicast, so assign different voices to each character in the book. But probably most importantly, I can download the whole thing as wav files or mp3s. And the big difference with something like Amazon Virtual Voice is I own what I've created with 11 labs, it's a commercial license, so I can put them into book funnels, audio delivery service. I can put them on my website. You can add them to a Kickstarter, stick them on YouTube or just give them away for free if I wanted to. And in terms of publishing reach, they're doing a lot. We were kind of stuck with either self publishing YouTube or Kobo, who are superstars and just super open. But one of the game changers that's happened in the last few months is you can now add them to Spotify, which, you know, they've come in as the big disruptor for Audible and Amazon. I mean, you've done that recently with the book that we produced together. How's that been?
- [10:12]
Joanna Penn
Death Valley, which has been on the feed, you can listen to a couple of chapters and that's using my voice clone. We'll come back to the voice clone in a minute. But as you mentioned, it's the mainly I think the ownership of the files and the Spotify distribution because at the moment it really is only Google's auto narration and elevenlabs that you can use legitimately on Spotify through Findaway Voices. It will soon be known as Inaudio. But basically going wide with these files, you cannot use the AVV files anywhere else, as you said. So I think that's incredibly important because of course we can talk forever about how to make audio, but it's also about selling audio, isn't it? I mean that's what we want to do.
- [10:56]
Simon Patrick
And for anyone who's dealt with kdp, Kindle Direct Publishing or Audible customer services, I don't probably have to say how the experience was. So another reason I love ElevenLabs is their support's been brilliant. There's this discord I mentioned where there's just dozens of super helpful and patient people giving input. But even if that's not something you'd want to get into their plain old customer services team, you know, reply quickly, it's personal, they're helpful, they've got amazing documentation. And then just the overview, stepping back a little bit, the fact that and it's not just 11 labs but AI audio, the fact we can create well narrated audiobooks for 100 to $200 plus a few days learning and production on each one is. It's just incredible. I took my two, two boys, I've got three kids, took two of them to a local Comic con recently and there was the self published author there with a single beautiful book. He clearly spent so poured his heart and money into this thing and there were beautiful cover bookmarks, giveaways. And then I saw he had an audiobook and we got talking about it, he'd got it professionally rated and he opened up and said what it cost? It cost £7,000, Joe. And I honestly wanted to cry. I like, I genuinely get emotional about it even now. It's just like I want Us as authors, publishers, to put our time and energy and money into creating incredible stories and getting our words out into the world and just make everything around that as simple as possible, using tech where we can.
- [12:23]
Joanna Penn
Yeah, and I just want to comment on this because one of the reasons we timestamp these episodes and I always now say the date and have done for years in my intro is because I'll have people email me and say, oh, but you said this. And I'm like, yeah, but when did I say that? And for example, in 2014, when I started audiobook publishing on ACX, when they opened up to UK authors, they were the only thing out there and they were the bee's knees. You know, they were what we were doing and we had a much higher royalty rate. There were very few audio books around. And you could make that money back, say the amount of money you mentioned there, you could make that money back quite quickly. Now I know some people will be saying, oh, but I make that money back. And I'm like, well, yeah, if you're an established author, if you have a popular series, if you know that you already make that kind of money from audiobooks, then you can. But we're in a different era. You know, in 2025 there's a lot more audio. And of course AI is a double edged sword. There is going to be more audio than ever before. And so the question is, how do we make that money back? And if we lower the cost, then we do also lower the amount of revenue we need to make to offset that. So I think that's really important for people to keep in mind. So if you're like, oh, but you said you make tons of money on audio, so. Yeah, well, that might have been 2014 to, I don't know, 2020.
- [13:45]
Simon Patrick
Yeah, yeah, absolutely. And you know, it's going to move on fast. But now is an extraordinary time to be just, you know, I love audiobooks, I love good audiobooks and the fact that I can help me make those now is, is very exciting to me.
- [14:01]
Joanna Penn
It's super fun. Yeah. So you and I both have a reasonably technical background so we can use these tools. And to be fair, you said wonderful documentation. I am terrible at reading documentation, as in I just don't read document, I just jump in and give it a go. And then if I can't figure it out now, I Probably just ask ChatGPT, how do I do this on 11 labs? Like literally I will do that.
- [14:24]
Simon Patrick
They've got their own AI that actually talks to you. So you can ask L as they call it.
- [14:28]
Joanna Penn
Oh really?
- [14:29]
Simon Patrick
It'll chat you through, it'll talk to you live about how to fix stuff.
- [14:32]
Joanna Penn
Okay, well that's good to know. But there are people who are like, yeah, but I don't know anything about AI audio. How does it work? So obviously we're in an audio medium right now, but can you give a few key elements and tips for authors if they want to use 11 labs for this AI narration?
- [14:47]
Simon Patrick
Yeah, I've got five tips for you. One is so go in and kind of check it out and have a look at. Try the trial and there is a creator package that you will get for half price for the first month that I would say just for exploration is worth getting 11, $11 just to have a little bit of a play with it. Because getting familiar with the platform, it's a little bit intimidating because it does lots of different things right? It's, it's got voice changing, it's got sound effects, it can dub video. Only interested in the studio tool. And as soon as you go into that studio tool it will start to feel familiar. You can click create an audiobook, you can drop your epub that you will have your book in there and basically instantly see how this thing works, break it into chapters, applying a voice, clicking play and it will just start to work. The warning though is this Creator package, the $22 a month is what it turns over is not good enough to create professional audiobooks. So this is my first tip. You need the pro package which is $99 a month because that is what outputs 192kbps. That's the technical specification that you need to go on book funnel, to go on Spotify. Frankly to have something good to share your own on your own website, you only get that by doing the $99 a month package. You get about 10 hours of audio creation in that. So that could for a lot of people make a make a book. If you're doing a 70,000 word novel or something, certainly you could fit that in there that the hours roll over though. So you can either like wait for month two and have enough hours to do it, but as soon as you're done with your book you can downgrade to a five dollar a month package and not be spending that 99. So don't worry, it's trapping you in there. Just know that first is you need the 99amonth pro package to produce your audiobooks. Second tip is really spend time choosing or making your voice. And I think you, you had an experience with this, Joe, where you kind of, you try out and you give little tests of things and go, right, I'm going to commit to this voice to use it. And then you realize two or three chapters in, after listening to it and editing it, I don't like it annoys me. And I've had that experience too. So use that first month kind of on the creator package to really play with voices. Generate your first chapter in like 5 or 6. Really get familiar and comfortable with a voice that you want to use so that you're not wasting time and credits to generate it. When you get into producing something, I think, you know, don't get overwhelmed. Have fun with it. It's amazing hearing your voice come to your, your book come to life in audio. I feel give it an hour. And the Studio tool, forgetting about all the rest, the studio tool is pretty intuitive. If you have got the level of tech ability to do something like typesetting in Atticus or Vellum or use Scrivener, you can absolutely master using Studio. It's really intuitive. And yeah, just don't get overwhelmed. Have fun with it to begin with. But my warning with that, and I think we discovered that as we worked on Death Valley is it still takes time.
- [18:15]
Joanna Penn
Right.
- [18:16]
Simon Patrick
AI assisted artists and authors, which I love your phrase. This isn't some one button wonder. Right. Your novella was what, six hours length?
- [18:27]
Joanna Penn
My novel, Death Valley, it was like 70,000 words. Yeah. So, yeah, six.
- [18:33]
Simon Patrick
I think it was six hours. Six and a half hours. That took took 18 hours of editing.
- [18:38]
Joanna Penn
Yeah. And this is where people get confused because with avv, so the audible virtual voice. Because there is no control.
- [18:44]
Simon Patrick
Yes.
- [18:45]
Joanna Penn
You literally do click one button and it goes live. I mean, there's almost no point in proof listening to it because you can't actually change it. And again, time stamping for June 2025. But with Studio, as you say, you have such fine control that let's say you want. Well, you can obviously add pauses, but let's say you want a breath in the middle of a sentence or you want emphasis change. You kind of direct it, don't you? I feel like it's more directing than anything else.
- [19:12]
Simon Patrick
That's the word I use. Yeah, directing. It's like you're directing an audiobook. It's.
- [19:15]
Joanna Penn
So it takes time. But if people are like, well, why would I bother? I mean, again, does it just come down to cost or is it also the, the actual quality as well?
- [19:25]
Simon Patrick
Well, if you're doing nonfiction, it is borderline one Click wonder. It's, it's in there, it will deliver amazingly and you need to listen to it once and you're good to go. If, if you've spent like a year or two writing a book, you think about the effort we put into making it look good in the typesetting, the covers and everything. A day or two to, to listen to it, to refine it and make it represent your vision. I don't think it's time wasted. I think for, for me, I'm only interested in high quality audiobooks that do the book, the story justice. And yeah, I want to be proud of it. I want to Abby to be proud of it. As you said, it's like I'm the director of this book and it's, it's more like self narrating and managing it than it is, it is getting it just done for you. And I just highly encourage people particularly who are fiction writers to think about the voices they want for it to spend, to be prepared to spend two or three days working on the book. It is so rewarding to get something that comes out the end that you are proud of in a completely different format from, from the way you've been publishing before.
- [20:39]
Joanna Penn
Yeah. And just on the proofing because if you work with a human narrator, you will be doing proofing. So you listen to the audio and then you're like, oh, not quite happy with that bit. Then you find the timestamp and you explain what it is you want changed and then you send them back to the human, the human re records and then you do it again. So I mean the process I think is probably pretty similar in terms of the amount of time taken, like three times amount of finished audio. But as you say, you can do it yourself. And there are areas that do help. For example, if someone, if there's a character name, you can fix that once, can't you?
- [21:13]
Simon Patrick
In the whole audio pronunciation for any words. Actually it really struggled with creosote.
- [21:19]
Joanna Penn
Yeah.
- [21:21]
Simon Patrick
And then. And it does little random things. I think our favorite was when it pronounced desert as dessert.
- [21:26]
Joanna Penn
Yes, it kept doing it. Just would not stop wanting some dessert. But what are some. I guess what are some other tips?
- [21:34]
Simon Patrick
Yeah, I think, I mean the big one right now, and this is only pertinent to those listening to this as it's broadcast, is if you're wanting to do an audiobook for your fiction book, you should wait if you're doing non fiction. As I said, the existing models are amazing but last week their version 3 model released and it is a game changer. The initial reactions are, I can never go back to version 2 and I thought version 2 was great, but I.
- [21:59]
Joanna Penn
Was going to say Death Valley's version 2, so I think it's still quite good.
- [22:02]
Simon Patrick
No, I know. And I'm like, It's like this pain, this sunk cost thing of. I've just done a few of Abby's books in version two, it's like, oh, man, what do I do with this? But, yeah, version version three, from an expression and liveliness in the voices, but also from a control and direction perspective, is changing the game. It wasn't even supposed to come out for a couple of months, so they're moving forward with this stuff, with this fast. But it is absolutely the most expressive yet. So the initial reaction has been amazing. It's just early testing of converting basic text to speech, but every generation is very different. The voices, as we said, don't work with it. That's all going to come. It's very early research testing. They've got a big job to tame it. But the real reason to wait is it's got one massive feature upgrade, which is what I've been waiting for for at least a year, and that is you can add emotion tags. So previously, both you and I, when we were playing with this, if we wanted someone to whisper, sometimes it would figure it out from the text. Other times we would literally be adding, he whispered, she whispered, he shouted, he said excitedly. You know, we were kind of gaming the system now, and they have been promising it for a while. We can, in square brackets, add to the text. Whispers, shouts, says thoughtfully says in a British accent. Right. There is just this whole world of things it can do that we can much more effectively work as a director, particularly for dialogue and emphasis, where we can be telling it exactly what to do. And even from the outset, there is a button that will read the text and put in suggested tags throughout the book. This is not like a massive task. It will be putting them in, and it's figuring out when someone's excited, when they're thoughtful, when they're quiet, when they're loud. And by putting those in square brackets, the AI is reading those instructions but not reading them out loud. So it is the big breakthrough, I think, in terms of us creating audiobooks that are just exactly how they. We want them to sound.
- [24:18]
Joanna Penn
No, that is. That is really good. I'm looking forward to that as well. But let's wind it back for people. You mentioned nonfiction quite quickly, that basically it's great for that, right? Now I was just thinking about this because somebody asked me this question the other day and you might find it obvious, but they said, well, what do I do about the table of contents or all the other stuff, like a lot of URLs in my text or my images. And so I think one big tip, especially with non fiction and even the back matter in fiction is you just, you can, when you upload the epub, you can just delete those bits. I feel like people forget that you have control on these not, not all systems like you don't on AVV, but on 11 labs you just delete that table of contents. And what I've been doing with my URLs is getting rid of a lot of them within the text because there, a lot of them aren't necessary. But then also some of them I will change. So like the creative pencil.com forward/11labs, which is my affiliate link for 11labs, I will change the, the dot to a.for.and. and then say forward slash for, for forward slash. I actually type out the, the words.
- [25:23]
Simon Patrick
It's even getting better at reading those naturally.
- [25:26]
Joanna Penn
Okay, well that's interesting because yeah, I found that that is something because sometimes when you do a URL, the words don't read naturally unless you're doing them.
- [25:34]
Simon Patrick
Yeah. I mean one of Abby's books is how to Be a Books Grammar. Basically she's an influencer in the book world, which if you're a dad, the daughter is an influencer. You want it to be the book world. It's like so wholesome. Like there's all these tags and things of things that just make no sense to be read out. So in doing those, we had to spell those out just so that they made sense to someone listening. So there is changes and you can completely change the front matter, the back matter, the bits around it to be something that's going to work most effectively when it's delivered on the platforms you want. And you can create different versions. You can have one that you're putting into 11 reader, you can output it separately as one that you're delivering through your website and just want to keep people within that ecosyste. Yeah, lots of options.
- [26:15]
Joanna Penn
Yeah. And I think it's really important for people to remember with audiobooks that it is an adaptation. However you're doing it, it is a different product. Yes, it is based on your words. But with Death Valley for example, I would say to you, oh well, let's just rewrite. I'll just rewrite that sentence. Yes, you know, because it will just be easier for me to rewrite it and it will keep the same meaning, but. Or get rid of that line because it's just not. Not necessary. You know, when I would say sometimes a beat, I'd write a beat of silence. It's just not ne in an audiobook.
- [26:46]
Simon Patrick
Exactly that. And you have that luxury as the author. And this is why people doing it themselves is. Is wonderful when producing your book for you can't take those liberties.
- [26:55]
Joanna Penn
That's a good point.
- [26:56]
Simon Patrick
So that's. That's what. And so you were super helpful giving me that feedback. The other thing. And we'll talk about 11 reader in a bit, I'm sure. But just remembering that the changes we make to the text like that are also visual changes. So in the app that 11 labs provide for consumers, you're listening to it, but it is also scrolling through the text. So spelling things strangely to get them right and putting things in caps does affect the reading experience. So there's all kinds of considerations to take there.
- [27:27]
Joanna Penn
That's actually. I didn't realize that. But of course that's correct. But yeah, we'll come back to 11 reader. But you earlier, you mentioned like five tips. I don't think we've made it through five yet.
- [27:36]
Simon Patrick
I thought we got through them all.
- [27:37]
Joanna Penn
Oh, did we? Okay, I think just. Just recap the five things.
- [27:41]
Simon Patrick
So one was just make sure you get the pro package when you're actually producing. It's got to be the $99 package to get audio book quality output. Make sure you're spending time choosing your voice. Don't get halfway through, so generate some of those. Don't get overwhelmed with it. Have fun. Just give it a chance. If you're using Atticus or Vellum, then I think it's something that you can handle. It's going to take time. Tip number four, be prepared to spend two to three times the length of the book proofing it, crafting it. If you care about having a quality book that you're proud of as the outcome. And last of all, you should be waiting. So version three. For fiction books, you should wait for this version three to be available as a production model where you can use the voices you want with it. It's going to be consistent and you're going to have this amazing new level of control with the tagging.
- [28:37]
Joanna Penn
Okay. No, that is five. Great. Okay. So let's then come to the voice clone idea, because of course, you mentioned earlier that you've licensed your voice. We used my voice clone For Death Valley, my J.F. penn narrator voice. And I am still going backwards and forwards. I'm kind of on the fence as to whether or not to license that publicly. So, I mean, I know there's people listening who are audiobook narrators either for their own books or for other people's books, or there might be people listening, have different accents. Because I think this is really interesting too. You and I have quite English voices, to be fair.
- [29:13]
Simon Patrick
I'm proud of it.
- [29:15]
Joanna Penn
Yes. I'm proud of it because, for example, my husband, he's a New Zealander. His accent is kind of hybrid English Kiwi. And that's a type of voice that you, you wouldn't get on 11 labs right now anyway. I mean, getting there.
- [29:30]
Simon Patrick
So there are already within English, there are maybe a hundred accents available, but.
- [29:36]
Joanna Penn
This is interesting in itself. Okay, so within English. But ElevenLabs also has multiple languages.
- [29:41]
Simon Patrick
Yeah. Like one of the other things on v3 model that we didn't mention is currently there's about 30 voices with the version 2. Version 3 is already 90 languages.
- [29:51]
Joanna Penn
90 languages.
- [29:52]
Simon Patrick
90 languages.
- [29:53]
Joanna Penn
And within that there are more accents. Right. Whether you want a soft Scottish accent or a really hardcore Northern Irish accent. For English, I mean, there are and in every single language. So I would encourage people to think about that. When you're thinking about the voice for your book, it may be that that voice isn't there yet. So the question is if people listening, if they want to license their voice, if they want to do a voice clone. What are some of your tips for that?
- [30:18]
Simon Patrick
Super. Okay, well, first let me thank you for letting. For being a guinea pig as I tried this out and offered the service to others. So for me, it's been amazing getting this bonus income that I totally didn't expect to get. For Abby, it's been life chang genuinely in that she is the most popular English, British female voice.
- [30:38]
Joanna Penn
Is she called Abby?
- [30:39]
Simon Patrick
She's not on the site. So I'm going to give you a tip in a minute to not do what I'm about to do. But she's Amelia on 11 labs and I've got two voices, which is Christopher and Benedict. And it's one of the tips we'll get to in a second. But for her, she's earning enough from her voice that she could quit a toxic job and go full time writing. Like, wow, extraordinary. And we've just published her latest book yesterday because it's freed her up to do that. So that's amazing. So again, in terms of tips, if you're Recording your own voice, whether you're going to use it yourself or thinking about sharing it with others and potentially monetizing it. First of all, the quality of the recording is essential. You want to be using a good microphone, you need to be doing it in a quiet place. There are lots of tools to to clean it up and improve it, but nothing is going to compare to something that's delivered well to a good microphone and carefully recorded and when you're delivering your voice. So I've got a group of people who've come, I've built this little recording studio at the end of the garden, and my advice to them is the delivery needs to be varied but consistent. So I generally get them reading a book, a novel. If they're authors themselves, I'll get them to read their own book, as I did with Abby. And what you want to do within that is give variations in terms of tone and volume, so whispering through to energy and delivering it as though you were reading to an engaged audience. But you do not want to put character voices on. That's really important. So deliver it consistently in terms of the voice you're using, but vary the delivery of it in terms of giving it all energy and moving and doing low and high. The AI will pick up on all of that, but it gets very confused if you've then done character voices because it doesn't know how those fit in with how you speak if you're doing it yourself. The kind of cheat code for improving the quality if you haven't got a really good mic or haven't got a quiet area to do it is Adobe Podcast. So it's a free service. They have an enhanced speech function that you can get two hours free and you can put your recording of your voice in there and massively improve how good it sounds. The tip for that is specifically, don't put it like 100% treatment. You'll see you get an option to vary how much is applied. You want kind of 70 to 90% of their enhanced speech applied to your voice, or else it sounds too obviously affected by AI. But if you need to up it, brilliant. I personally spend a couple of hours kind of using pro tools to tighten things up and the rest. But that will do, honestly, 70, 80% of the job, making it sound great.
- [33:34]
Joanna Penn
And then like I did so far as we record this again, my JF pen voice is my voice and I'm the only one who can use it. So that is, I think you. And then there's like another step for if you want to license it and put it in the voice market, isn't it?
- [33:50]
Simon Patrick
Yeah. And I think the first challenge of that is genuinely a moral evaluation kind of what you're going through at the moment, Joe, which is if you want to monetize your voice, there are two options and I won't get too much into the detail, but two options you have to choose for it to make any money. And the first is that you have to not switch on live moderation. And that means that. So live moderation is a service because these guys, they've got iconic voices like Burt Reynolds and Mayor Angelo and the rest, they, they don't want those like swearing and saying stuff. So they've got this second tier of control of what can be voices can be used for called live moderation that stops it Swear. Like you try and make Bert swear and he'll just go instead.
- [34:36]
Joanna Penn
Right.
- [34:37]
Simon Patrick
Which is hilarious. Yeah, it's lovely. But as soon as you turn that live moderation on, your voice is. Is unavailable to anyone wanting to make an audiobook. It's not going to be available for conversational AI. It basically cuts off 90% of the ways it could ever make money. Okay. So there is this moral judgment you need to make which is, am I prepared for my voice to be used to say almost anything?
- [35:03]
Joanna Penn
I say almost anything because basically hate, hate speech or sexual content or anti religious things. Things.
- [35:10]
Simon Patrick
Yeah, for certain, some of those things. There is a kind of core tier of control where they are stopping some of that. But it's only the live moderation option that's going to absolutely eliminate the risk of it though. You have to decide one, are you prepared to let your voice go out there and it be used to say all kinds of things. Like the first one of the only times I've ever heard my voice in the wild, a friend of mine phoned me up and said, I've just heard you narrating a Saddam Hussein history documentary. It's just like, what is going on? Hilarious and like, it was actually quite good, but it could be used for anything. Right. The second option that you have to consider is how long your notice period is going to be when you share your voice. You can say either I can have the rights to instantly withdraw this from being used up to two years. And quite cleverly, they actually pay you more if you're prepared to have the longer minimum of two years. But vitally for me as a producer, I'm not going to start using someone's voice for audiobook series when I might not have it to Use in three months time. Right. So I instantly filter anything less than a year's notice period and I generally only pick two years because that's the longest I can, I can get. So if you want to monetize your voice, you have to turn live moderation off and you have to be giving a two year notice period, in my opinion.
- [36:34]
Joanna Penn
Yes, lots to think about there. And as we said, I have yet to make a decision on this. I'm still basically thinking that I won't do it, but it is very interesting and I will certainly use it for my own books.
- [36:46]
Simon Patrick
So just a third tip on it would be just be safe. Right. I'm naming my voices because I'm kind of doing this publicly, but all my family are geared up with a literal code phrase that my mum knows if someone phones up and it sounds a bit like me, but she's not sure I will share that with her. So on the whole, do not share your public voice's name and connect it with you as a person. Like forget about voice recognition for telephone banking, for example, that's turned off. And last of all is do your research. So Alex Newton and I, the guy from K Lytics, just a great guy, we did a brilliant weekend's research just saying what voices are most popular and what descriptions work best and what should we call ours and what are the sample that people can listen to to and, and think about all of that. And I'm producing materials to help people think that through as well.
- [37:35]
Joanna Penn
Yeah, I think that's great. And I mean, certainly if somebody listening is already a professional audiobook narrator, then I can't see why you wouldn't give this a go as potentially extra revenue because your voice is already out there doing its thing.
- [37:52]
Simon Patrick
Absolutely.
- [37:53]
Joanna Penn
And you'll get ongoing revenue from this. But as we head towards a close, we do need to quickly come back to eleven Reader. So eleven Reader is an emerging place to publish audiobooks to either through the studio for the audio files, like I did for Death Valley, which is on 11 reader, but you can also upload ebooks and then listeners can choose the voice. And back in 2020, when I wrote my book on AI, I said at some point there will be an app where they can just choose whatever voice they want to listen to my book. And this is it. This is it.
- [38:26]
Simon Patrick
I remember you saying it, Jo.
- [38:28]
Joanna Penn
Yeah, exactly. And I put it in there and I was like, why can't I everybody choose the voice they want to listen to? So just tell us a little bit about 11 reader and what you think is worth it at the moment because it's really pretty new, isn't it?
- [38:42]
Simon Patrick
Yeah, it's super exciting. It's just, it's been in kind of testing for a year with people accessing, but it's an app that you'll find on your iPhone. Android Store, just search for 11 reader. It's also just starting to be available on the web as well. But it's the consumer facing side of ElevenLabs. So the stuff we've been talking about, ElevenLabs Studio is for creators, producers. This is where the general public are mainly experiencing elevenlabs voices. And you, as you said, you can drop in pretty much any content like PDFs, eBooks, web pages and send emails to it. I'm using, I put it in the, you know, on the side in my car. I will chuck a PDF that I've just received from someone and have it read to me while I'm driving along so I can kind of process it. It's turning any, pretty much any text into speech and that's super useful. But right from the beginning it's also offered books and I reckon, I don't know, maybe close to a thousand, perhaps more in there now, yours being some of them. Right, Jo?
- [39:37]
Joanna Penn
Yes, I, I've been slowly kind of uploading my books there and a lot of indie authors taking advantage of it. But we should mention that whatever your politics, the.
- [39:46]
Simon Patrick
I thought we'd come to this.
- [39:47]
Joanna Penn
Yeah, we have to. Melania, who is of course the wife of the President of the United States, as this is recorded. It doesn't matter what your politics are. The fact that is this very prominent woman has used a voice clone of her quite distinctive voice to do her memoir, also called Melania. And she has basically said this is the future of publishing. You know, here's my AI voice clone and it's on 11 reader. So yes, you can find Death Valley, you can also find Melania.
- [40:15]
Simon Patrick
You can indeed. And amazing. It's there for direct sale that you can pay, I think it's $2 for it. You can listen to it and just so upfront about it, it's fascinating.
- [40:26]
Joanna Penn
Yeah, I just thought pretty amazing. And that was a tipping point, I think for me because it means that it's going mainstream and they got a lot of press for that, didn't they?
- [40:36]
Simon Patrick
Absolutely. So basically you can see it like Audible or Spotify, except you can choose what voice you want to narrate, as you said. But authors for authors, it's an amazingly simple way to offer an audiobook you don't even have to go through the studio production process that we've been talking about. You can actually just sign up to 11 or reader publishing and upload your book. Boom. They'll review it, they'll publish it. And I think it's like an opening beta pricing structure right now. But $1.10 you're getting when someone reads 11 engaged reader. Engaged reader, which is really, obviously, I.
- [41:12]
Joanna Penn
Would say to people, you must read the terms and conditions of any site that you ever upload anything to. I think this is very important to mention again, also, things change and so keep reading the updated terms and conditions. I would also say that you can upload your epub to 11 reader, but that is your ebook that you are then licensing to be read as an audiobook. Yes. So if you are in KU and your ebook is exclusive to Amazon, you can't upload that to 11 reader because it's exclusive.
- [41:42]
Simon Patrick
And we have just taken Abby's books out of Kindle Unlimited so we can put them in 11 reader this week.
- [41:47]
Joanna Penn
Ah, there you go. And this is the thing, I think where we're going, I guess, with this whole episode and the focus on audio is there are more and more places where you can publish and sell and use audio for marketing. And if you are exclusive in any form, you do lose out on some of that. So just have have a consideration there. So before we go, you have courses coming. You also offer services to authors, so tell us about those and where people can find them all online.
- [42:14]
Simon Patrick
Oh, wonderful. Thank you, Joe. First, I'd be a very neglectful father and publisher if I didn't mention that Abby's latest book went live yesterday. Stolen Legacy. I've got the proof sitting on my desk right now. I'm very proud. So, yeah, Abby HopePatrick and Deadly ever after series. You can find it on Amazon and very soon 11 reader. And yeah, you can find me on 11 reader, as we talked about earlier, you can search for my voice, maybe compare it to what has been listening to me live. I'm Christopher on there. You'll find me reading a sample of Wordsworth as the sample. But yeah, the course is something new. We've started up a new website to deliver them, but I keep getting asked to teach people the kind of skills that I've learned as a publisher and AI for Authors being the key one. So AI Audio for Authors will be the first course. It's going to cover everything people know to get themselves not just onto 11 labs, but all the platforms. So it's going to be covering ElevenLabs and all the clever stuff you can do with it and how you can use it for your own direct selling. But also it'll talk about Amazon Virtual Voice, Google Play, Apple, etc. And it's going to have, have training on how to record your own voice clones and monetizing them if you want to. So yeah, it's a new family business. Claire, my wife and the kids are getting involved. It's exciting. And it's called Novel Productions. It's not just novels, it is non fiction too, but I just liked the name. So the website is Novel Productions. And yeah, we're, we're stealing from you, Joe, I confess in terms of the idea of being an AI assisted art as an author production house.
- [43:46]
Joanna Penn
Oh no, I love it. It's not stealing, it's modeling.
- [43:48]
Simon Patrick
Yeah, modeling and, and you know, we're embracing new technology to create great books and audiobooks to free up authors, to double down on being human as you extol us to. So I've held off. I was about to publish it and then version 3 of 11 labs came out and so I don't want to train anyone on anything that's, that's not going to be the best in a couple of months. So right now if you go to Novel Productions, there will be a waiting list that you can sign up to. There's going to be news as things develop there. I'll be giving insights and various free bits of material. And yeah, you mentioned services too. You were my first beta tester outside the books that I publish. So we're still weighing up how affordable we can make it. But I've got a couple of audio engineers who are part of a band that I lead that are kind of ready to be helping people create books. The philosophy is very much, I'd rather teach people first and if they, they don't want to, then do it themselves. We'll see how we can help. But I'm beta testing that with authors. So email me at simonovel Productions and that will get through to me. But Joe, with your blessing, I think the first place I'm really going to offer that ability to get your books made for you is probably going to be your patron members. So encouragement to people. Check that out. It's an amazing community. Sign up there and I'm regularly commenting on things.
- [45:05]
Joanna Penn
Brilliant. Well, thank you so much for your time, Simon. That was great. Great.
- [45:08]
Simon Patrick
Thank you, Joe. It has been such a pleasure.
- [45:14]
Joanna Penn
So I hope you found the discussion with Simon interesting and that you might give Elevenlabs a try for your audiobook. It's at elevenlabs IO or my affiliate link is thecreativepen.com elevenlabs so let me know what you think of today's episode. Please leave a comment on the podcast show notes@thecreativepenn.com or on the YouTube channel, or email me joannathecreativepenn.com send me pictures of where you're listening or your favourite cemetery or churchyard in an audiobook. Double whammy. This Monday I'm talking to Jules Horne about writing for audio. So today's was I guess slightly more technical and on Monday it's a more craft based episode around the same topic of producing audiobooks. In the meantime, happy writing and I'll see you next time. Thanks for listening today. I hope you found it helpful. You can find the backlist episodes in show notes@thecreativepen.com podcast and you can get your free author blueprint@thecreativepen.com blueprint if you'd like to connect, you can find me on Facebook and X at the Creative Pen or on Instagram and Facebook. Fpenauthor Happy writing and I'll see you next time.