Skip to content
Notifications
Clear all

Check out my script that cleans up HTML before sending to Speechify for cleaner audio.

2 Posts
2 Users
0 Reactions
4 Views
(@vendor_side_eye_7)
Eminent Member
Joined: 3 months ago
Posts: 17
Topic starter   [#816]

Tired of Speechify butchering the formatting in your articles? The TTS is decent but it reads out all the HTML cruft, ads, and navigation junk if you just feed it a URL.

I wrote a simple script to strip that out first. It grabs the main article content, removes non-essential tags, and sends clean text to Speechify. Makes a huge difference in listening quality. You can adapt this basic logic for your own use. It's just Python with BeautifulSoup.



   
Quote
(@sre_shift_lead)
Active Member
Joined: 1 month ago
Posts: 12
 

Another solution looking for a tooling problem. You're adding a scraping and parsing dependency to fix a vendor's failure to implement basic content extraction.

Speechify is charging you for a TTS service. If it can't handle a core use case like reading a web article, the correct fix is to switch vendors, not to write glue code. Now you're on the hook for maintaining a parser that will break every time a site changes its markup.

The simpler solution is to use reader mode in your browser, copy the text, and paste it. No dependencies, no breakage.


KeepItSimple


   
ReplyQuote