@fastfinge

Admin

completely blind computer geek, lover of science fiction and fantasy (especially LitRPG). I work in accessibility, but my opinions are my own, not that of my employer. Fandoms: Harry Potter, Discworld, My Little Pony: Friendship is Magic, Buffy, Dead Like Me, Glee, and I'll read fanfic of pretty much anything that crosses over with one of those.
keyoxide: aspe:keyoxide.org:PFAQDLXSBNO7MZRNPUMWWKQ7TQ

Location Ottawa

Birthday 1987-12-20

Pronouns he/him (EN)

matrix @fastfinge:interfree.ca

keyoxide aspe:keyoxide.org:PFAQDLXSBNO7MZRNPUMWWKQ7TQ

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@luiscarlosgonzalez @cachondo @FreakyFwoof @amir It has the same problem with speed.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@luiscarlosgonzalez @cachondo @FreakyFwoof @amir I didn't try Kokoro, because it cannot achieve a real time factor of 1 on CPU. By that I mean, to be fit for consideration with a screen reader, a text to speech voice must be able to generate one second of speech in one second or faster. In general, Kokoro takes two seconds to generate one second of speech. So it's not suitable.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@clv1 @jscholes @cachondo @FreakyFwoof @amir The issue is that both of these are effectively concatenative or parametric, rather than formant, systems. So they will never be as intelligible as eloquence.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@VE3RWJ Shrug. Nobody else has reported that issue. Probably a false positive from malwarebites.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@jscholes @cachondo @FreakyFwoof @amir That's my assumption because the only things that really need a 32-bit compatibility layer are speech synthesizers and braille devices.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@FreakyFwoof @cachondo @amir Yeah, you can get AI to modify the 32-bit addon for you. That's how I got the first two eloquence prototypes; it helped me understand the problem and what approaches would work and what wouldn't. If you give it the 32-bit orphius addon, and the 64-bit eloquence addon, it should be able to understand the working approach to make an addon 64-bit, and make the modifications itself. The reason to give it the 64-bit eloquence addon as an example is so it doesn't decide to go down the GRPC route and include protobuf and a bunch of other nonsense.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@jscholes @cachondo @FreakyFwoof @amir It was mentioned in the roadmap NVDA released a while back.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@cachondo @jscholes @FreakyFwoof @amir They don't have much choice. A lot of the libraries NVDA depends on are stopping 32-bit support this year.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@jscholes @cachondo @FreakyFwoof @amir My understanding is that when this comes to addons, it's going to require some kind of secure addons API/layer. And it won't be ready for 2026.1, or maybe not even 2026.2.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@FreakyFwoof @cachondo @amir You should be able to get either Gemini or Codex to help you, depending on what AI you have access to. The workflow would be:
1. download gemini-cli or codex-cli, and get them installed and configured.
2. clone all of the sourcecode from github.com/fastfinge/eloquence_64/
3. Delete the tts.txt and tts.pdf files, so you don't confuse it with incorrect documentation.
4. Find any API documentation for orphius that's available, and add it into the folder.
4. Run codex-cli or gemini-cli, and tell it something like: "Using the information about how to develop NVDA addons you can find in agents.md, and the information about the Orphius API I've provided in the file Orphius-documentation-filename.txt, I would like you to modify the code in this folder to work with Orpheus instead of eloquence."

It will go away for five or ten minutes, ask you for permission to read and write the files it's interested in, and then give you something that mostly works. Now, build the addon, run it, and tell it about the errors and problems you have and ask it to fix them. In the case of errors, include the error right from the NVDA log, and for bugs and problems, tell it exactly what it's doing wrong, and exactly what you want it to do instead. Keep doing this until you wind up with a working addon.

Think of AI as a particularly stupid programmer, and you're the manager in charge of the project. You should be able to get this done without paying anyone.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@cachondo @amir I've heard from a second hand source that they are, yes. But I haven't verified that.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@pixelate @PepperTheVixen If you have a sample of someone talking while chewing gum, you can absolutely make that happen.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@pixelate @PepperTheVixen If you give chatterbox-tts an ASMR recording to clone, you can absolutely get it to make lip smacking noises.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@PepperTheVixen The reason it's grating is because unlike Eloquence and dectalk, Espeak only uses formant synthesis for the vowel sounds. For consonants and plosives, it instead uses concatenative recordings based on human speech. That's why even when you switch to a voice that sounds less sharp, the "t", "b", "p", and other sounds are still too sharp. This seems to be the primary cause of the fatigue most people experience while using ESpeak.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@svenja I vaguely remember writing something like that a while ago. The list I linked has all of the games I remember putting in that comment, though.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@Landon205 There's already addons that do that.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@svenja Was it this? gist.github.com/Molitvan/50e3b5060ab9465b1da895155d5c0480

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

The State of Modern AI Text To Speech Systems for Screen Reader Users: The past year has seen an explosion in new text to speech engines based on neural networks, large language models, and machine learning. But has any of this advancement offered anything to those using screen readers? stuff.interfree.ca/2026/01/05/ai-tts-for-screenreaders.html #ai #tts #llm #accessibility #a11y #screenreaders

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

@pitermach Even Mona only indicates it after reading the text. IMHO, it should be before! I can see myself replying to a toot in a language the author doesn't speak.

🇨🇦Samuel Proulx🇨🇦 @fastfinge@interfree.ca

So one of the problems with automated #translation based on #AI is that it's in this weird, awkward place now where it's not good enough to seem native, but it is good enough not to be immediately obvious. I had forgotten I set my browser to automatically translate pages in several languages to English for me. Then I clicked on a #fanfic, read the first couple chapters, and was getting really annoyed why one character kept changing Gender's, and the name of a location wasn't consistent from chapter to chapter. Turns out the author was writing in #Spanish, I hadn't noticed the language tag, and when I clicked the browser just automatically translated without clearly telling me. Thank goodness I realized, just in time, before I posted a comment on her work pointing out the issues with writing quality and offering editing help! Yikes! That doesn't mean that I'm against Machine Translation or even think it's a bad thing. But as it gets better and better, and starts living in this awkward uncanny valley, we really need to carefully rethink user interfaces. Maybe disable all form inputs until the user clicks "I'm aware this was translated" somewhere? I had the comment all written, folks; I was that close to posting. Maybe put "translated from" in some obvious place like the title bar? I don't know what the answer is, but I do know that we need to be putting way more thought into it.

❮ Previous page Next page ❯