Would you call a network packet generation tool Pakigen?
Abogen – Generate audiobooks from EPUBs, PDFs and text
71–80 of 85 posts
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#72How does this compare with the lightweight kitten TTS model which was recently on HN?
https://news.ycombinator.com/item?id=44807868
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#73I've been using Kokoro TTS with the CLI app, audiblez, mentioned in the "Similar Projects" section of the README. The model is fast and delivers impressive quality for its small size. Some issues I have faced, however, are: a) It doesn't distinguish periods at the end of sentences from the dots in abbreviations such as "Mr." or "Mrs." The result is an awkward pause between "Mr." and the name. b) It doesn't handle ell…
I fixed that here: https://github.com/cpttripzz/audiblez
The main problem with Kokoro is how flat and lifeless it sounds. But it is very fast. I prefer Chatterbox tts but it is around 20 times slower and will not work without a GPU
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#74can I choose any voice? would love to read software engineering books in voice of Morgan Freeman, or maybe even better, Scarlett Johansson
no, but this will allow you to: https://github.com/cpttripzz/Chatterblez
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#75My biggest selling point for this would be, that the volume is probably the same throughout the whole text. I am listening to audiobooks to fall asleep, and many voice actors go from very quiet to loud in conversations. It may be good narration, but it's sometimes to quiet to understand, so I need to increase the volume only to be woken up by some loud lines later.
So I imagine generated audiobooks to be good in that regard. Another option would be to have a "normalize volume" setting at audible, or other services.
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#76Nice! As an aside, while this tool can be used to create an audiobook from a book you have in text format, for your private consumption, having an author employ something like this to create files for distribution is extremely risky, even if they acknowledge its use and intend those files to only be available on their website. Indie authors struggle a lot to promote their works, and the new normal is that potential r…
> and the new normal is that potential readers, the polite ones[^1], use the slightest hint of AI usage to discard their title and move on... Is that the new normal? My impression is that when it comes to reading text, nobody cares as long as the final product is good. People don't want AI- written books, but people have been comfortably listening to AI voices reading text for a long time now. Text-to-speech isn't re…
Sadly, it is common enough these days. There are reports of authors that set up a stand to physically sell their books, and members of the public ask "is this AI-written? Who made the cover? Is this cover AI?"
> My impression is that when it comes to reading text, nobody cares as long as the final product is good.
Maybe so, but it only takes a vocal minority to ruin things for an author. And that minority tends to use anything, even a non-overtly-critical mention of AI in social media.
The consensus right now is that using LLMs for fixing grammar and typos is acceptable. I personally use them for word completion (specially the devil incarnate which are the prepositions on/in), but tend to discard suggestions that improve flow, sentence structure and readability, because those increase the odds of triggering "AI detectors". In fact, I've found a renewed taste for unconventional sentence structure and unconventional punctuation; things that three years ago, before the LLM boom, I really didn't care for.
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#77Earlier quoted context omitted.
Don't worry. Australia will probably ban it for some reason anyway. Better to be free. Btw, Don't look into the name of a famous python formatter or you might be offended.
"Abo" carries the same cultural impact as "Paki" in the UK, and isn't a word in its own right, let alone a very commonly used one. Completely different kettle of fish. Seeing as you want to derail this into some free speech rant - it's just distasteful. You really think anybody who wants legislative control over freedom of speech in Australia gives a damn about Aboriginals getting offended?
Intent matters and your phrasing "Seeing as you want to derail this into some free speech rant" is fundamentally offensive to me. Censor yourself.
Go fight for chat control under the guise of caring about others. It's been really successful so far. "Free speech rant"...
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#78I've been using this to try to make audiobooks out of various philosophy books I've been wanting to read, for accessibility reasons, and I ran into a critical problem: if the input text fed to Kokoro is too long, it'll start skipping words at the end or in the middle, or fade out at the end; and abogen chunks the text it feeds to Kokoro by sentence, so sentences of arbitrary length are fed to Kokoro without any guard…
You could try implementing a character count limit per chunk instead of sentence-based splitting. A hybrid approach that breaks at sentence boundaries but enforces a maximum chunk size of ~150-200 characters would likely solve the word-skipping issue while maintaining natural speech flow.
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#79You will want to reconsider the name if you plan to have a presence in Australia or New Zealand. "Abo" is an ethnic slur similar in offensiveness to the N-word.
Thank you for bringing this to my attention, I genuinely appreciate you taking the time to share this important feedback. As the repository owner, I want to clarify that "abogen" is simply a shortened form of "audiobook generator," which is what this project does.
I completely understand your concern, and I'm grateful that you pointed this out. It's clear that your comment comes from a place of wanting to help, and I really value community members like you who look out for potential issues.
The name was chosen purely based on the technical functionality (audiobook generation), and I had no awareness of the unfortunate similarity you've mentioned. As English is not my native language, I sometimes miss these cultural nuances that native speakers would naturally catch. I appreciate your understanding that this was entirely unintentional.
Thank you again for the thoughtful heads-up
Re: Abogen – Generate audiobooks from EPUBs, PDFs and text
#80I've been using this to try to make audiobooks out of various philosophy books I've been wanting to read, for accessibility reasons, and I ran into a critical problem: if the input text fed to Kokoro is too long, it'll start skipping words at the end or in the middle, or fade out at the end; and abogen chunks the text it feeds to Kokoro by sentence, so sentences of arbitrary length are fed to Kokoro without any guard…
Hey, can you share an example book or text so I can test it?
Regarding "abogen chunks the text it feeds to Kokoro by sentence", that's not quite correct, it actually splits subtitles by sentence, not the chunks sent to Kokoro.
This might be happening because the "Replace single newlines with spaces" option isn’t enabled. Some books require that setting to work correctly. Could you try enabling it and see if it fixes the issue?