[HN Gopher] Show HN: Oration (iOS) turns pdfs into audiobooks
___________________________________________________________________
Show HN: Oration (iOS) turns pdfs into audiobooks
Hello HN community! I'm excited to introduce a project I've
recently launched: Oration, an iOS app designed to convert PDFs
into audiobooks. This idea was inspired by my experiences as an
engineering student with ADHD, struggling to engage with dense
academic papers. Relying on Text-to-Speech tools, despite their
robotic quality, was a workaround for me and others with similar
learning preferences or challenges, such as Dyslexia. Recognizing
the limitations of existing tools--difficulty with complex formats,
inability to skip over citations or footnotes, and inadequate
handling of tables, graphs, and figures--I developed Oration. Our
goal is to refine these areas continuously, offering both
summarized and full versions of PDFs for a more accessible learning
experience. Oration aims to serve as a high-quality, user-friendly
platform for auditory learners and those who find traditional
reading methods challenging, with features akin to popular
audiobook apps like Audible or Spotify. How Oration Works:
1. Download the app and sign up using either a username and
password or through Google, with a 2-week free trial that doesn't
require a payment method. 2. Upload a PDF document.
3. Within about 5-10 minutes, you'll receive a notification that
your Audiobook is ready. 4. Listen to your Audiobook
directly in the app or through a browser-based web player, which
also facilitates easy sharing with friends and family. Also,
to emphasize - all audio generated by the user is yours to own!
We're working on some updates to easily export .MP3 files of
Oration Audiobooks you create For an example of how the web player
looks and functions, check out this link:
https://player.oration.app/75e079c1-bd7e-4a16-8e02-23636837a... I
believe Oration can significantly benefit those who prefer or
require alternative learning formats. We're committed to enhancing
the app's functionality and user experience, so feedback and
constructive criticism are always welcome. Thank you for
considering Oration, and I hope it proves to be a valuable tool for
you or someone you know.
Author : adi4213
Score : 34 points
Date : 2024-02-09 15:51 UTC (2 days ago)
(HTM) web link (oration.app)
(TXT) w3m dump (oration.app)
| FloatArtifact wrote:
| I appreciate your work however not allowing the owner of the book
| to own the audio generated through your product does everyone a
| disservice. Everything seems to be locked into the app or the web
| interface. If that's a misunderstanding on my part I apologize.
|
| So if we pay for your product we should own what it produces for
| the sake of long-term use and accessibility. Please allow the end
| user to download in a standard format the audio like MP3 / MP4.
| adi4213 wrote:
| I'm sorry, I didn't make this clear! You very much own the
| audio generated! That was my intention from the beginning and
| will make sure that the app along with our terms and services
| reflect this prominently. I'll make some updates today to make
| it straightforward for the user to download an .MP3 of what
| they create on Oration
| FloatArtifact wrote:
| Thank you for clarifying! Best luck with your business and I
| hope to put your service to use.
| atlas_hugged wrote:
| Nice. Too bad all my uploads failed
| adi4213 wrote:
| I appreciate you trying it out and sorry that this was your
| experience! I'd be more than happy to look into what happened
| if you wouldn't mind sending an email : support [at]
| trurecord.com At the moment, the free trial has a limit of 50
| pages / PDF (I'll make this more clear in the app) and requires
| selectable text (although I'm working on adding some OCR in
| soon)
| checker659 wrote:
| Does it work with math formulas?
| adi4213 wrote:
| It's definitely a work in progress - but something that active
| development is being focused around. The way this is being
| handled in an upcoming update involves a few things - an OCR
| tool identifies math formulas, applies a bounding box and takes
| an image. That image gets sent to a multimodal-LLM which
| attempts to "describe" the formula reasonably. While not yet
| perfect, this is something I anticipate to improve quite a bit
| soon. The same approach is going to be applied to tables,
| graphs, figures, and images.
| mdaniel wrote:
| I would value a "notify me when it comes to Android" link, since
| your example is pretty good but not enough for me to buy an iOS
| device and the "Sign up" just unhelpfully points to the appstore
| (I say "unhelpfully" because you obviously do have a web
| presence, given the example player and the fact that clicking on
| the sample title just redirects back to
| https://player.oration.app implying that one _could_ be logged in
| to the website)
|
| Actually, having written all of that, I would value just being
| able to submit things via your site, since based on your
| description it doesn't do any on-device processing so why do I
| even need on app?
| thrill wrote:
| In the sample on the website the abbreviation inside the
| parenthesis is skipped leading to the use of LLMs without it ever
| being initially defined. Not a big deal to anyone familiar with a
| term but of course papers on new subjects might keep the end user
| more engaged by not skipping that initial definition process. The
| audio displayed sounded very natural! How would it work for
| fiction and multiple voices (future capabilities?)?
| aloneindecember wrote:
| It's certainly an interesting and helpful idea. Kudos for working
| on the idea, and it will be exciting to see the progress in a
| year or two.
| kanodiaashu wrote:
| I am a grad student and I was going for something similar with
| converting papers to text which could then be used in an audio
| app like speechify with this -
| https://github.com/kanodiaayush/make-doc-listenable . I love the
| idea of this and will try it out, good luck!
___________________________________________________________________
(page generated 2024-02-11 23:00 UTC)