11–20 of 27 posts
You may want to give https://serenade.ai a try, they have browser support (might be chrome only? not sure), it's good enough, It has the " click publish" feature, and if it doesn't work then you can say like "show inputs" and it will show numbers next to each input so instead of saying "click publish" you say "click 14" etc...
* "Open Bank of America"
* "Login with saved password"
* "What's my savings bank balance?"
Yeah, I know it's fraught with security challenges and is likely acceptable only if using local models. Still, anything out there?
Assuming this does not yet exist: If anyone is interested in building something like this (that works offline) please let me know, I'd like to join. I have some experience building web extensions but unfortunately not the time to develop & maintain this on my own right now.
I control my browser (actually my whole computer) with my voice. I'm not aware of anything specific where you could say "click publish" and it would intelligently find the published button, though I haven't looked. What I use is a combination of vimium (a vim browser plugin, there are a few) and talon ( https://talonvoice.com/ ), either just relying on the vim shortcuts but with my voice, of for specific domains maki…
I can say the words "click reply" and this message will be sent.
Same here. Sadly, my dad is beginning to lose sight in both eyes now and has trouble operating essential websites (e.g. his bank's webpages). Does anyone know of browser extensions that enable a high-level voice command language? I'm thinking commands like: * "Open Bank of America" * "Login with saved password" * "What's my savings bank balance?" Yeah, I know it's fraught with security challenges and is likely accept…
You may want to give https://serenade.ai a try, they have browser support (might be chrome only? not sure), it's good enough, It has the " click publish" feature, and if it doesn't work then you can say like "show inputs" and it will show numbers next to each input so instead of saying "click publish" you say "click 14" etc...
Where does their revenue come from?
I control my browser (actually my whole computer) with my voice. I'm not aware of anything specific where you could say "click publish" and it would intelligently find the published button, though I haven't looked. What I use is a combination of vimium (a vim browser plugin, there are a few) and talon ( https://talonvoice.com/ ), either just relying on the vim shortcuts but with my voice, of for specific domains maki…
Dragon (dictate/NaturallySpeaking/professional/whatever they are calling it this year) has the ability to do this in conjunction with their official browser add-on, but it is an absolutely miserable product otherwise and I would not recommend it. I can say the words "click reply" and this message will be sent.
Most people go south with Dragon when they expect to be of the speak the keyboard or expected to be a perfect transcription. The reality is, it's like dictating to a good typist with a little bit of hearing problems. And like this hypothetical typist, you get worse results if you yell at it.
From what I can tell, Dragon, and I suspect most other speech recognition environments work best if you use them for dictating text and have enough commands supporting text editing. Dragon did a good job with what used to be called "Select-and-Say". It was a form of editing that worked with speech model and not some bastard grammar hack Forcing the editors keystroke commands to do a given job.
Assuming this does not yet exist: If anyone is interested in building something like this (that works offline) please let me know, I'd like to join. I have some experience building web extensions but unfortunately not the time to develop & maintain this on my own right now.
Same.