Settings

Theme

Show HN: Readability for web and PDFs with TTS and local AI summary

github.com

4 points by ldenoue · 2 comments

Reader

1 thread
ldenoueOP

weekend project that uses the latest Chrome Summarizer API, but also YOLO to process PDF pages and find images, tables, and math formulas.

Readability (Mozilla) is used when you open regular web pages, but PDF.JS (also Mozilla!!) is used to render each page, run YOLO region detection and then generate a clean HTML. Math formulas are rendered as Latex, and tables are rendered into HTML by detecting their structure using Texo/FormulaNet.

Finally, you can read out loud the readable articles/PDFs using another local TTS (I prefer PocketTTS personally, but wanted to try the newly released and tiny Inflect TTS as well, so it's an option).

Let me know if you find this useful.

I should probably publish them to the Chrome and Firefox stores.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection