[_def]

tangent but i vibe coded a webapp that pulls article texts and runs tts via kokoro. Its interface allows me to read the article text while the current paragraph is highlighted + autoscrolled while the audio is playing. All of this runs on a cheap vps. Works surprisingly well, as long as you are fine with consuming it "later" (conversion needs some minutes)

[onaclov2000]

I've been very happy with @voice aloud on Android to convert a page, (but most often for me) a PDF into spoken audio, sometimes I'll watch it auto scroll what it's converted. It's robotic but I've gotten so used to it I don't really worry much anymore (though I have played with voice clone stuff some and have really been tempted to use that). Anywho just reminded me of the app I have been using for probably a decade (don't quote me ;)).

Having the option on my desktop might be nice tho!

[soco]

How is your voice handling pipeline emojis and "leftwards rounded arrow with hook" bullshit any AI slop will contain and any reader will insist on fully reading aloud? I gave up reading webpages because of this, I can't focus on the actual text because of all formatting embellishment. I sought and sought but haven't been able to find an Android app or browser extension able to AI-filter through webpage garbage yet - and I'm too lazy to try to vibe-code something for myself.

[onaclov2000]

I've not used it excessively on webpages, the ones I have, I start reading then change my mind and decide to listen, but haven't observed the emoji issue. Then again, maybe I tend to skip over listening to AI generated (or at least overtly obvious?) content. I also have dealt with listening to technical content on PDFs and it sometimes tries to read out x's and o's from a plot, particularly annoying driving ;) guess it hasn't ever bothered me enough to just not use it. I have slowly experimented here and there looking to build a pipeline of text ingest (thinking I could use LLM) to convert certain text (like a plot in my earlier example) into a verbal description, a plot about this thing with emphasis on showing this fact. Or basically hey take this text and make it more digestable by audio, but I haven't experimented a ton.

Ultimately yes garbage in garbage out, but I've found enough value in using it, it's been good enough for me to suggest it's use, and hasn't caused me to search for another variant of tts on phone.

[Paradigm2020]

Link please