I am far quicker at reading than listening.
While I can utilize speed-reading techniques for some content somewhat faster than I can listen, it is an all-hands-on-deck situation attention wise and extremely sensitive to interruption.
On the other hand I can push 3x or faster depending on the narrator for audio content in most situations and 2x while doing nearly anything (the only exceptions being literally trying to carry on a conversation with a person or driving fast on a mountain switchback road).
I don't do "ordinary" reading particularly well due to my own brand of vision issues + ADHD/neurodivergence/whatever label is in vogue. This is a bit sad for me, but I've obviously got workarounds.
I haven't tried anything so far that I actually liked so my answer to "what's the best quality I have found?" is none.
The reverse though, OpenAI's Whisper for speech to text has been amazing, far exceeding my expectations.
Having just looked again I found a list at huggingface that I will be poking through in my spare time soon.
https://huggingface.co/models?pipeline_tag=text-to-speech&so...
I am genuinely curious though: what do you do with the information you absorb? Are you able to retain all of it and use it at will? If so, do you have any tips on how to do that?
No I don’t have eidetic or whatever the version of that is for audio or text. Closer to it when I was younger than I am now. I have a feeling this is something you can train with effort but not exactly sure what that effort is or if I have the motivation to try it.
To remember the most out of reading you have to engage with the material. Keep notes while reading or after, try to summarize what you have read after each session of reading or at the end of each chapter or each day. Ask questions about the material. Physically write these notes and questions down, ideally with actual pens and paper. Additionally engage with other people about what you have read vocally. Reading, writing, and speech engage different but connected pieces of your brain. Engaging with material in multiple modes reinforces memory from multiple directions as does the practice of summarizing, questioning, and discussing. Gets you into somewhat subconscious habits of paying attention to material differently.
But also, not everything is worth remembering. If I need a recording of the material i already have it on paper or an audio file, it doesn’t have to be accessible to my consciousness from my own memory when it’s just right there easily found.
Those two things (audiobooks on my phone, the default feature to enable play at 2x-3x speed) have vastly increased the information I absorb.
Now if only someone could come up with a screen/document reader with a decent text-to-speech and decent content filtering, it would be truly magical (read just the bulk text not and don't vocalize every single piece of text, most of which are major distractions to flow and don't need to be read)
Part of the reason I'm learning a bunch of ML things is so I can make this for myself.
On that topic, does anyone know of a really good, open, text to speech model? All of the ones I have been able to find have ranged between garbage and mediocre, none near "good enough" for the thing to be useful to me.