Text-to-audio for accessibility — where are the gaps?

I'm partially dyslexic. Long text has always been difficult for me — not impossible, just slow enough that by the time I reach the bottom of a page, the top has faded. Since high school, I've been converting articles, papers, and reports to audio so I could actually absorb them.

Over the years I've tried everything: screen readers (functional but robotic), browser extensions (limited), cloud TTS services (good quality but expensive for heavy use), and various read-aloud apps.

None of them were quite right. Most are designed for occasional use — read this one article, listen to this one page. They're not built for someone who processes a significant chunk of their reading through audio every single day.

The gaps I've personally experienced:

• Natural voice quality matters more than you'd think. Robotic voices are fatiguing over long listening sessions. Your brain works harder to parse them, which defeats the purpose.

• Speed control is essential. I listen at 1.3-1.5x for most content, but slow down for dense technical material. Most tools make this an afterthought.

• Offline access is non-negotiable. I convert articles for flights, commutes, and areas with poor connectivity. Cloud-only tools fail exactly when I need them most.

• Cost becomes a factor for heavy users. If you're converting 5-10 articles a day, per-character pricing adds up fast. This is an accessibility tool, not a luxury — pricing should reflect that.

I eventually built my own tool out of frustration, and it turned into something bigger. I recorded a quick walkthrough showing how it works — converting a blog post to natural audio in under a minute, automatically parsed and generated on my desktop:

But I'm curious about the broader community:

• If you use text-to-audio for accessibility (dyslexia, ADHD, visual impairment, or just preference), what's your current setup?

• What's the single biggest frustration with existing tools?

• Does natural voice quality actually change how much information you retain, or is that just my experience?

• How do you feel about AI voices for accessibility vs. human-recorded content?

This is personal for me. I want to understand how others navigate this, because I think the tooling can be much better than it is.