Skip to content

aldrshan/Book2Audio

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

54 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Book2Audio

Where I am

I am leaving this one public for posterity sake but... This project was rebuilt and expanded using Django to provide a db and other more better features. The new version includes a speed reader that displays a single word at a time. This can be sped up to 5000 WPM. There is also an auto update for the db pulling from online sources on a weekly basis. Furthermore Chat GPT is integrated for the voice which is the best I have found for reading text. That being said, if you know a better TTS engine I am all ears. If you are interested in the new build please send me a DM and we can colaborate.

Where I am Going

My todo list includes:

Creation of a front end allowing cloud selection (google, AWS, Azure, Watson) voice selection and monitoring of process.

splitting text to manageable size for s3 buckets

automate download and splice audio

auto update project guttenberg csv

use open ai to give a book summary

integrate dalle to provide visuals

Integrate video conversion to

connect to social media for automatic upload

The end goal

is an automatic conversion of public domain books into audiobooks by TTS engines. The best so far is Open AI TTS-HD

About

TTS reader for public domain books

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages