Automating Immersive Reading

I couldn't find it exactly in the docs. Sorry if I missed it.

If you align these and then pull onto koreader via opds or other way, will audio work over Bluetooth there too? Along with the highlighting.

The Storyteller mobile apps have great support for this, I think. They have fully fledged audiobook players and ebook readers, and you can switch between the two with one tap. And then of course you can also double tap on a sentence and start playing from there, with the app highlighting the currently read sentence.

I supposed I should add: it's also, obviously, fine if this just isn't for you! Lots of people get a lot of value out of audiobooks (e.g., I really like to listen to audiobooks in the car or while running), but like to switch to reading when it's an option. And lots of people find readaloud super valuable, whether because they have a print disability or neurodivergence that makes reading challenging, or just because they like the experience of being read to. But lots of people are in neither of those groups!

- Would it help with reading comprehension? Speed? Enjoyment?

- If the audio was your own synthesized voice, would that help comprehension and immersion?

- If the audio was in a voice very different from your own, and you used this system for several hours a day, would it change your natural inner reading voice, or even some other aspect of your self-perception? I don't believe I've experienced Such a tight coupling between thoughts driving external responses before; I didn't expect to do so until real-time brain scanning got a lot better than current SotA.

- While reading, I frequently speed along and then jump back a word, sentence, or paragraph to slowly review it. In this system, the audio would slow down as I read back through more slowly, almost sounding out words along with me. I just read a book filled with the names of obscure french villages, and I couldn't just ignore them - instead bogged down in sounding them out and trying to guess how to pronounce them. Having a system sounding them out with/for me would have been awesome. This assumes the system is good at pronouncing things in various languages (mostly solved problem), and picking sane defaults when pronunciation conflicts arise (mostly unsolved?). In those cases, how hard would inferring be? Google translate is pretty good at generating localized pronunciations, but TTS systems struggle.

- Specifically for non-technical reading, it would be interesting to try having a very low level of ambient noise backgrounding the speech, driven by an LLM analyzing the text for obvious cues. Tavern sounds, rushing of wind in the mountains, crackling campfire, or even music generation (creepy dungeon etc etc)... When you pause reading for a moment to look away from the book, the speech obviously stops - but the tavern sounds continue. Might help people 'lock in' who normally get distracted from whatever they're reading.

When we do roll out multi-level granularity, it will indeed be something that you can configure yourself, including how each level is indicated (e.g., you might want to set a background color on the sentence and underling the word) and whether a each level is indicated at all!

The "spread out" highlighting is a really neat idea, I don't think I've heard that suggestion before!

The current Storyteller alignment algorithm actually does do just that! We use Whisper to transcribe the audio to text, and then use error-align[1] to align on the text.

There are a few disadvantages to this approach:

1. Whisper only supports ~25 languages, and only about 10 of those very well. We want to support more languages, and Massively Multilingual Speech supports "1000+" 2. Whisper's timing outputs are not very good. We want to do word-level highlighting, like in the demo at the top of the post, but in order for that to be a good user experience, those timings need to be very precise. Much easier to do that with CTC!

CTC Viterbi is the tried and true forced alignment algorithm for good reason. It's not really that it's heavier duty than running Whisper and aligning on the output. Rather, it's like you stop Whisper early, before it does the final step of actually producing text, and step in and say: take the data you just calculated and use it to produce _this_ text, specifically. And then, since it produced _your_ text, you don't have to do anything else, you just use the timestamps directly.

The only reason Storyteller never used it in the past is because I couldn't come up with a good way to do the boundary search I describe in this post! This is super important for books in a way that it may not be for your oral reading transcript use case, because chapters can be (and often are) out of order between the ebook and audiobook. But once I worked out the n-gram RANSAC approach, it became much more tenable.

[1]: https://github.com/corticph/error-align

"Immersive reading" seems to be the industry term for this feature — I used it here because I though it was most likely to be recognized by a wide audience. Personally, and within the Storyteller ecosystem, I call it "readaloud," which I think is at least a little bit more useful of a phrase.

Also, disability isn't binary? Some people have an easier time reading text than others — is your argument that books should remain less accessible to those people for whom it's harder because you don't personally feel like they should need it?

And then there are _lots_ of people that just enjoy reading this way. Audiobook production is its own art form, and many people like experiencing the text and the audio together. For some people it helps them focus in a noisy environment, for some people they find they can read faster with the narration, and some people just enjoy it.

Every single time I post about Storyteller, there are multiple people in the comments insisting that this shouldn't exist because no one should ever consume books differently from how they do. I don't understand it, honestly. If you don't want to read books this way, that's totally fine! You can even still use Storyteller — it works great with plain EPUBs. Why the need to make others feel bad for the way they engage with stories? The world is a better place if more people read more books — discouraging people from reading books in the way that feels pleasant and accessible to them makes the world worse.

I think if you feel compelled to instruct people you don't know to "stop their current habits" because you don't personally understand their needs or wants, perhaps you should reconsider your current habits, yourself.

Also, it's just fun to have the audio narration as you read. I typically set the speed to like 2.5x when doing readaloud.