[New Add-on] Vision Assistant Pro: Your Interactive AI Copilot for NVDA (Powered by Gemini)

So I just installed the addon from the addons store, pasted in the API key and nothing seems to happen. When I tried to perform OCR on a PDF NVDA just says not connected.
I tried creating a new project in Google AI studio, same result.
Any idea on how to get it working?

I feel like I missed the first week of A.I. class and showed up on quiz day. When I go to Google Studio and hit the get API key button, it goes to an empty list of keys for imported projects. When I then hit the create API key, a modal pops up requiring a name and imported project--a combo box that's empty, with the "create" button disabled. Tried in Chrome and Firefox. Is this expected, and I have to create a project, or are browser extensions getting in the way, or what?
Thanks!

It translates one sentence at a time and I have to press the key combination every time, which is not convenient. Make it like the nvda translator to turn on and off, instead of pressing a key combination for each sentence.

Have to agree; real-trime translation of this quality is just what the doctor ordered. Question is, is it feasible?

I would recommend not implementing automatic updates or any update system directly in the add-on, as this is done automatically by the NVDA add-on store, and users can enable or disable automatic updates there.

Thanks for this most indispensable add-on, i just used the OCR to describe my full screen and got a very nice description, i tried it again a minute later to get a full screen description. it says API key missing. what's up with that? is there a quota limitation of how much you use the add-on or am i missing something. and by the way i am using the very latest version of this add-on

Hi Mahmood! I would like to congratulate you on the excellent add-on. Keep up the good work! I have some suggestions that would make things much easier: the possibility of having a screen to place multiple prompts and then being able to switch with a shortcut key. Sometimes, I want to know what's in a photo, then something in a game, and it would be useful to already have these prompts predefined by the user and just keep switching. Another suggestion would be an option so that when it showed the result, it would just speak, without showing a dialogue or window. It's quite useful to know information quickly without having to switch windows. Thank you!

Salve e complimenti per questo fantastico Add-On. Segnalo che, quando effettuo una trascrizione audio di un file .mp3, viene notificato l'errore 400, con richiesta di controllare la propria chiave API, che ovviamente è corretta. Ho provato a cambiare l'estensione del file audio ad esempio in .wav e la trascrizione funziona, dunque ritengo dipenda dal modo in cui l'estensione .mp3 viene vista dalla chiave Api, spero possiate risolvere, grazie mille.

Intanto grazie per aver risolto brillantemente l'errore 400 sui files .mp3. Ho inoltre trovato davvero meravigliosa e fantastica la funzione per descrivere i video da Url di YouTube ed Instagram. Sarebbe super se si potesse fare anche per X ed altre piattaforme ed anche, se si potesse fare con i video in locale riprodotti sul proprio PC, so che ci potrebbero essere problemi di Privacy, personalmente, se richiesto, sono disposto a concedere tutte le autorizzazioni necessarie, sarebbe davvero meraviglioso. Infiniti e sinceri complimenti e grazie di cuore!!

Hello again! I will never stop thanking you for this amazing Addon! Furthermore, I hope he is well, if I am not mistaken his area is Iran and I know what is happening, I sincerely hope that he is as good as possible and that he is safe.
I would kindly ask if it is possible to implement video descriptions also for the TikTok platform, it would be truly incredible, given the efficiency I found for both YouTube, X and Instagram, although on the latter, I found some Download errors, in practice it seemed not to recognize some Urls. But, in any case, it is a wonderful function, can it also be implemented for TikTok? Thank you very much and all the best, with great respect and sincerity!

This is fantastic! I'd like to donate, but I don't use the platform that is provided. Maybe consider Paypal like NVDA uses? I also appreciate that this is fully accessible to braille users!

I finally got around to trying this add-on, and so far it's excellent! It took me a minute or 2 to figure out the API key thing, but once I got that, I've tried a few modes, and am impressed with the speed and quality of the responses so far.

A few Questions

1. As a low vision user, I noticed that when you bring up the Settings screen for VA Pro, I can navigate through it via NVDA and keyboard, but nothing shows up on the screen. It would be helpful if this window showed up visually, like the rest of the windows do when you use the add-on. Not sure why nothing shows up for the Settings screen.

2. Can there be an option for a dark theme for the windows that appear for low vision users, or those who are light sensitive?

3. When I scan a file or document, does it do the whole thing, like multiple pages, or just the first visual page like when doing standard NVDA + R?

4. When scanning a video link, is there a rough video length we should limit it to? Just trying to figure out how long it would take to process a video. I fed it probably a waaay longer video than I should have, and got a key error. Understandable...

5. Is there a keyboard shortcut to bring up a menu of the add-on's functions directly, in case we forget a specific letter? I know you can do this via the add-on submenu, but maybe a direct menu command to bring us right there?

I think this is all I can think of for now, but I will definitely be playing with this more. I like it though. I'd also love to see a PayPal option for donations, as almost everyone has PayPal.

Hi, wondering if this addon could take input from a scanner OCR it and then drop it in a document or speak it out loud? I'm recommending NVDA to more and more clients and some of them use scanners. Thanks.

I cannot express how much I appreciate this add-on, and yourself for creating it. I have litterally disabled and/or removed at least 5 separate add-ons & applications that had similar functionality, but individually. For example, I had a translation add-on, an OCR add-on, etc.

I installed the 4.5 update from an NVDA add-on notification, and ironically installed it before seeing this post. Anyways keep up the excellent work. This add-on is even outperforming the latest build of Be My Eyes for PC. Which is a shame because BME used to be amazing.

Hello. I just saw there was an update to this add-on this morning, along with an NVDA update. I was able to install the NVDA update, but every time I try updating the Vision Assistant Pro add-on, I get a download failed error. I will keep checking in and retrying the update. Im guessing something simple changed with the NVDA update. Just FYI for now.

Thanks for the reply. I did just try the update again, and it went through this time. Thanks again.

Hello and again my most sincere, immense congratulations for this Add-On which is becoming more and more indispensable for my daily operations with NVDA. Since for me it is very important to be able to have a complete and detailed description of the images, I would like to suggest the possibility of carrying out this operation: I know that you can use Be my eyes, for example, or cloudvision, which however seems to have had problems, or even Image Describer, but the latter also has problems with the API keys and does not work very well. Thanks to his skill and his undoubted abilities, given the excellent functioning of Vision Assistant Pro, I am sure that he will have no difficulty in implementing this function, so that the images and also the writings contained in them can be described, given that he already does this with the text of the images and the documents, but I would actually like the description of the images themselves to be added, as I described above and it would be wonderful and wonderful if one could then interact with the AI as happens with videos or all the other functions, so as to be able to delve deeper with further questions. For example, I use ImageMagik with the command line to insert my logos in various positions and I have built many scripts for this and, when I have an image, knowing the entire description, I can have the AI ​​tell me in which position I can put my 200x200 png logo, where the space is free in the image in order to make it clearly present, without overlapping it with something or ruining the elements of the image itself. Furthermore, since with its fantastic add-on, you can describe the entire screen, I don't think it will be difficult for you to implement this function. I thank you sincerely and deeply for your wonderful work and I hope you will be able to implement this function, thank you very much again.