Show HN: New Audiobook Generator for Nvidia Using Chatterbox TTS

#1

Post by beboplifa » Sun, Jul 20, 2025, 6:03 AM UTC

I am an audiobook addict that coded this https://github.com/cpttripzz/Chatterblez. I am using it all the time and it works nice. I have only bothered to get it working on windows but it should be cross-platform as it uses pyqt, I would be happy for contributors to help get it working on macos and linux and also ATI and other video cards.

If you are stuck without a video card I recommend using https://github.com/cpttripzz/audiblez it can generate an audiobook in around 4 hours with a decent CPU

Show HN: New Audiobook Generator for Nvidia Using Chatterbox TTS
github.com

Re: Show HN: New Audiobook Generator for Nvidia Using Chatterbox TTS

#2

Post by BinaryIgor » Sun, Jul 20, 2025, 6:54 AM UTC

Interesting; I was thinking about creating something like that a few years ago - since I love listening to information a lot while doing some chores/walking - but back then, all available text-to-speech converters were unbearably robotic.

How much time does it take to convert a book/doc into audio using your approach? Also, as I understood it all runs locally, so you don't need to pay for any API access/usage?

Re: Show HN: New Audiobook Generator for Nvidia Using Chatterbox TTS

#3

Post by beboplifa » Sun, Jul 20, 2025, 9:22 AM UTC

BinaryIgor wrote: post #2

Interesting; I was thinking about creating something like that a few years ago - since I love listening to information a lot while doing some chores/walking - but back then, all available text-to-speech converters were unbearably robotic. How much time does it take to convert a book/doc into audio using your approach? Also, as I understood it all runs locally, so you don't need to pay for any API access/usage?

on an nvidia rtx 2060 mobile about half a day for a medium sized novel. Chatterbox TTS is really emotive, sometimes too much so.

Re: Show HN: New Audiobook Generator for Nvidia Using Chatterbox TTS

#4

Post by drewbitt » Wed, Jul 23, 2025, 3:05 AM UTC

With Chatterbox this finally feels almost possible. I find that I am sensitive to pacing issues which it often has. Kokoro was just alright. I'm using a tool I hacked together that runs Minimax Speech-02-HD which is still a whole other level, IMO, but not that cheap. Inworld-TTS-1-max is cheaper - I'm trialing it these days. async.ai seems promising too.

Thanks for the tool! I'm also quite interested in this space.