It’s odd they label the voices as “soprano” and “baritone,” because they don’t sound like it.
I suspect it’s to avoid labeling the speakers as “male” and “female.” What a joke.
Apple Books digital narration
231–240 of 244 posts
Re: Apple Books digital narration
#232I have to say that a number of audiobooks I've bought recently have been totally spoilt by the narration - and the AI voices on offer here all sound better than the humans involved in those books. I also remember reading, a couple of years ago, that Apple was working on improving the voices for Siri - resulting in me thinking "surely Apple has more important things to work on to improve Siri". I guess this was what t…
It's so true! It's such a tragedy when a really good book is ruined by bad narration. All of the Hitchhikers Guide books (except for the first one, which is masterfully read by Stephen Fry), are a good example, but there are tons of other examples. There's usually only one version as well so you can't even shop around for a version with a better narrator either.
If you can find it, look for the BBC Radio version of Hitchhikers, from the late 70s, early 80s. Each version has a slightly different variation on the story and the radio one is my favourite of the lot.
My friend had a copy of the scripts from the radio series and we used to use it as inspiration - "open the scripts at a random page and our band name will be the first thing that Marvin says ... Zootlewurdle - perfect!"
I've got them on a set of CDs somewhere, but have nothing that will play them...
Re: Apple Books digital narration
#233Will we see this level of voice synthesis in the public domain? Maybe I am out of touch but I found those examples very impressive - more impressive than the jobs vs rogan demo a few months back. But I am also saddened at a future where all this is locked up in corporate hands - obviously there is money needed and (licensed) data needed too which Apple can get at. Honestly I would rather eschew the ethics of it and j…
Not from the companies selling audiobooks IMHO. They will use this technology to save money on human speakers. If they release it into the public domain we'll end up with ebooks that can read themselves aloud and they'll lose part of the incomes from audio books. My Samsung phone can read ebooks with one of Samsung's voices right now, but it does an awful job at pauses. Basically, no commas. With a good voice I could…
I don't really think I could listen to an AI voice reading a book. Perhaps some technical stuff, but not fiction. Even the difference between a mediocre vs good voice actor is huge, and can mean the difference between finishing an audio book or stopping after a chapter.
Edit: to be very specific, a really good voice actor will take on different voices depending on which character is speaking, and will act out scenes realistically. I honestly can't imagine any AI being able to do that.
Re: Apple Books digital narration
#234I'm curious about the thinking behind "mysteries and thrillers, and science fiction and fantasy are not currently supported." Is it because these genres use more non-standard words? Or is there more risk of the Apple voice being used to narrate sonething inappropriate?
Re: Apple Books digital narration
#235Earlier quoted context omitted.
I find those slideshows unintentionally hilarious - ten photos of my kid interspersed with a flash photo of the back of the washing machine and some cable that's hanging down underneath my car, an accidental screen grab of a text message, all treated with the same importance and jaunty library soundtrack.
This made me LOL, as I’ve had this happen many times. But much less so in the past 2 years, around the time iOS Photos started integrating with Apple Music.
Actually now you come to mention it I haven't noticed it very recently - maybe I've stopped looking at those suggested slideshows, maybe I've turned a setting off without realising it.
Re: Apple Books digital narration
#236Earlier quoted context omitted.
"Our algorithm isn't stupid, it's the literature which is wrong" is not something I expected to read today.
Have you ever read a written passage out loud and failed because the text was too contrived and the nature of the intonation only became apparent after re-reading the sentence multiple times? I have, plenty of times. And in most of those times I got really angry at the author for writing "wrong". So yes, to me saying that the literature is wrong is nothing unexpected.
It depends. Is it technical writing? Then I agree with you. But literature is meant to make you feel a certain way, to paint a mood or a picture, or even to experiment with language.
The "AI" has trouble with that because it's fundamentally a machine for recombining already existing information.
Re: Apple Books digital narration
#237It’s the spaces between sentences and between pauses that need work. Usually a reader will take a breath or finish exhaling. Instead Apple’s audio drops to 0 db. It sounds unnatural. Mechanical.
Re: Apple Books digital narration
#238Earlier quoted context omitted.
Citation needed? TTS tools exist on all computing platforms these days. The difference with this recent release is just that it sounds better. Apple would not be creating a derivative work, whoever uses it would be. EDIT: It has occurred to me that they may have signed a deal as part of Apple Books that says they won't release tools of this nature. I don't know if that is the case, but that isn't the scenario I'm tal…
TTS tools are required for accessibility etc. However, "convert your ebook into audiobook with this amazing voice over" will run into issues. Amazon tried it: https://www.wsj.com/articles/SB123419309890963869
Yeah, I'm familiar with that. Amazon backed down from the fight. So there was no answer to the legal question.
EDIT: Also, since I can't get through the WSJ paywall, here is Amazon's complete statement from the time:
Quote:
Here is the full text of Amazon’s statement:
Kindle 2’s experimental text-to-speech feature is legal: no copy is made, no derivative work is created, and no performance is being given. Furthermore, we ourselves are a major participant in the professionally narrated audiobooks business through our subsidiaries Audible and Brilliance. We believe text-to-speech will introduce new customers to the convenience of listening to books and thereby grow the professionally narrated audiobooks business.
Nevertheless, we strongly believe many rights holders will be more comfortable with the text-to-speech feature if they are in the driver’s seat.
Therefore, we are modifying our systems so that rights holders can decide on a title by title basis whether they want text-to-speech enabled or disabled for any particular title. We have already begun to work on the technical changes required to give authors and publishers that choice. With this new level of control, publishers and authors will be able to decide for themselves whether it is in their commercial interests to leave text-to-speech enabled. We believe many will decide that it is.
Customers tell us that with Kindle, they read more, and buy more books. We are passionate about bringing the benefits of modern technology to long-form reading.
Re: Apple Books digital narration
#239Earlier quoted context omitted.
I wanted to make a human-like reading feature for our language-learning software. Training a model isn't too hard using something like https://github.com/coqui-ai/TTS . The weak link was the available free/open datasets. You needed a single speaker with a pleasant voice, 20hrs+ material from varied sources, recorded in a good recording enviroment with a good mic etc. For English, the go-to was LJSpeech, which doesn't…
Added a download link to the readme: https://github.com/dioco-group/jenny-tts-dataset/blob/main/R...
This is great! Thanks for sharing. How much did this cost you?
Re: Apple Books digital narration
#240I have to say that a number of audiobooks I've bought recently have been totally spoilt by the narration - and the AI voices on offer here all sound better than the humans involved in those books. I also remember reading, a couple of years ago, that Apple was working on improving the voices for Siri - resulting in me thinking "surely Apple has more important things to work on to improve Siri". I guess this was what t…
It's so true! It's such a tragedy when a really good book is ruined by bad narration. All of the Hitchhikers Guide books (except for the first one, which is masterfully read by Stephen Fry), are a good example, but there are tons of other examples. There's usually only one version as well so you can't even shop around for a version with a better narrator either.
I've learned to enjoy particularly robotic TTS narrations because after a while it becomes associated with my internal voice, and it feels like I'm "reading" the book versus elaborately produced audiobooks that are experiencially closer to enjoying a show. And feel less hesitation about listening at 3x speed. With practice, I can start layering on personality to different characters with neutral TTS voices.