Skip to content →

Month: November 2024

A Nice Enhancement for Voice Access on Windows

Published November 28, 2024 by Kelly Ford

As a matter of choice, not necessity, I try from time to time to use the various speech and voice input systems in operating systems. My ideal scenario is still to be able to use the computer by voice entirely as well as running a screen meter. I’ve not found a reliable solution as of yet that meets my needs completely.

I know there are combinations of solutions that have made great strides in this area largely using Dragon products and screen readers but as the basis of what I use, I try to use either Voice Access on windows or Voice Control on the Mac. Both platforms also have solutions, as I expect many know, for strictly text input.

I no longer recall how long ago this was but the Voice Access product on Windows did make one change that helps with using screen readers. As a start, Voice Access produces notifications of what Voice Access has heard so that screen readers can echo this back. It is fairly basic and in need of much refinement  it’s at least a start.

I am mentioning this here because in trying voice access this week, I noticed a change that is another step in helping Improve the experience. I do not know when this change was made to be clear. It is just that I noticed it this week. I also run Insider builds of Windows so if this does not work for you, that may be why.

When you’re trying to control the computer by voice, it is common to issue commands such as click and then an item that you want to activate. The challenge becomes that if there is more than 1 item with the same name, you are usually presented some experience to disambiguate what you want to click on.

When I first tried voice access, to the best of my recollection, the experience of identifying what you wanted to activate was not usable with a screen reader. It has been enhanced a bit so that now when that list of choices comes up, the list of choices is echoed back similar to how what Voice Access heard is repeated. Again this needs extensive refinement because it is kind of like a one time listen or read and Braille experience with no way to have the list repeated, step through the list in item at a time or otherwise understand what was said.

As an example of using the feature to identify what I want to click, here was what was read when I asked for the word paste to be clicked.

click paste. Which one?
There are 2 options available. (1) Paste, (2) Paste

Here is another example when I said “click login” on the Fidelity home page.

Click login. Which one?
There are 2 options available. (1) LOG IN, (2) Open login link

It is also worth noting that these disambiguation choices if using Braille appear as flash messages. For those unfamiliar with how Braille displays and screen readers work, this means that the messages stick around for a set period of time and then disappear from the display.

. Here is one last example when I tried to activate the OK button with my voice after running a spell check on an email message. Note, I intentionally replaced the actual email address with email@provider.com.

Click ok. Which one?
There are 2 options available. (1) OK, (2) Sent – email@provider.com – Outlook – 2 running windows

The experiences I’ve described work independent of what screen reader is being used.

Again this experience overall of using the computer with a screen reader and voice on Windows as far from finished. In fact one of the key experiences for correcting words that have not been recognized correctly does not work at all with screen readers. Voice access in fact gives the following notification when you try and correct something and a screen reader is running:

Alert: This experience is not optimized for use with screen readers. Say “Cancel” to exit.

Microsoft has a document on using Voice Access in general. If they have screen reader-specific documentation, I wasn’t able to find it.

If you do try Voice Access, two important hotkeys to know are Alt+Shift+b for toggling the microphone between sleep and awake and Alt+shift+c for toggling the Microphone off and on. When sleeping, the microphone remains on to listen for certain words. See the support article or say, “what can I say,” when Voice Access is running for a full list of commands.

Leave a Comment

No Big Finish, Giving Microsoft’s Recall a Try

Published November 24, 2024 by Kelly Ford

Microsoft released the Recall feature for users of Windows Insider builds. I gave the feature a try and made an audio recording with a roughly edited transcript. The short version of my experience is that I can get around Recall but am still trying to figure out how to read search results effectively with a screen reader, hence the title of No Big Finish.

Since this blog post is about an AI feature, I’ll offer an unedited version of Copilot’s summarization of my transcript as well. Overall the summary is reasonable but in my opinion misstates what I said about the Click To Do feature. I said I hadn’t figured out how it is supposed to work.

Perhaps because it was at the end, the summary also missed my biggest point entirely about still trying an effective way to use the search functionality of Recall and reading the meaningful text easily. Here is the Copilot summary:

The document is a transcript of a demonstration by Kelly on the Microsoft feature called “Recall.” This feature captures screenshots of your screen and allows you to search for information within those screenshots. Kelly explains that Recall was released as a test version for Microsoft Insiders on November 22nd. The demonstration focuses on the accessibility aspects of Recall, particularly how it works with screen readers like NVDA, Narrator, and JAWS.

Kelly describes the setup process, which includes signing in with Windows Hello, and demonstrates how to navigate the Recall interface using keyboard commands and screen reader feedback. The document details various functionalities of Recall, such as saving snapshots, opening Recall from the system tray, and navigating through captured images. Kelly also mentions some issues and limitations encountered during the demonstration, such as certain screen reader commands not working as expected and the need for further development to improve accessibility.

Kelly starts by explaining the initial setup, which involves a brief opt-in experience where the user grants permission for the computer to take screenshots. This process takes about 20 to 30 seconds and requires signing in with Windows Hello. Kelly notes that each time Recall is opened or used, the user is prompted to sign in with Windows Hello.

The demonstration continues with Kelly navigating the Recall interface. Kelly shows how to open Recall from the system tray and describes the various options available, such as saving snapshots, opening Recall, pausing the feature, and accessing more settings. Kelly highlights that the timeline feature in Recall displays the captured images, referred to as “memories,” and sessions, which represent the time periods during which the computer was used.

Kelly also points out some issues with the screen reader’s ability to read the titles of the snapshots automatically. Kelly demonstrates how to navigate through the list of snapshots and mentions that sometimes the titles do not read correctly on the first attempt. Kelly suggests using the home and end keys to navigate through the list and get the titles to read properly.

Additionally, Kelly explores the commands available for each snapshot, such as opening the associated application (e.g., Outlook), copying the snapshot, deleting it, and accessing more options. Kelly notes that some features, like the “Click to do” button, are not fully functional yet and require further development.

Kelly also demonstrates how to get more details about a captured image using Narrator’s command for image descriptions. However, the output is often gibberish due to the limitations of the OCR (Optical Character Recognition) technology used. Kelly suggests using other solutions like JAWS, Google’s Gemini, or Be My Eyes for better image descriptions.

Overall, the document provides an insightful look into the Recall feature, its current capabilities, and areas for improvement from an accessibility perspective. Kelly’s demonstration highlights the potential of Recall while also acknowledging the need for further development to enhance its functionality and accessibility.

Leave a Comment

Unlock Windows Efficiency with PowerToys Run

Published November 13, 2024 by Kelly Ford

Sometimes you make a handy discovery that makes you wonder why you did not know about it long before. I just had that happen with PowerToys Run, one of the toys included in the full suite of items in the electronic toybox known as Windows PowerToys.

PowerToys are a set of utilities that allow you to customize different aspects of Windows and offer functionality that is not directly built in. You can learn more in general and find details on installation in a handy Microsoft Learn article.

I installed the most recent version of PowerToys because I had read about something new known as Advanced Paste. That is not the discovery though.

After installing PowerToys, I used one of my more common shortcuts in Windows Alt+Space to bring up the system menu for an application. That menu is where you find entries including restore, close and the one I often use, Maximize. My web browsing windows in particular often get sized quite small and with responsive design much of the content I’m expecting has disappeared so maximizing the browser window is necessary.

Imagine my surprise when instead of what I was expecting, my screen reader communicated, “query, edit.”

It turns out this is the default shortcut for the aforementioned PowerToys Run. In short, this is like having a command line to do everything from choosing between open windows on your computer to performing quick calculations, file, and web searches, browsing the Windows registry and more.

Using PowerToys run

Using PowerToys Run is fairly straight forward. Press Alt+Space, enter some text and arrow through the results. You can start your text with various text characters to direct PowerToys Run what you want to do. The full list of text to use here is detailed in a Microsoft Learn article.

Some examples I am finding I have already incorporated into my daily use include:

  • <, that is the less than symbol: Window Walker, to browse through all the open windows on your computer. Start pressing down arrow after entering the less than character, or add part of the window name and then down arrow to shorten the list.
  • $, that is the dollar sign character: Windows Settings to, as you would expect, browse through all the different settings for Windows. As with Window Walker, just start pressing down arrow after entering the dollar sign, or add some of the text from the setting you want and then press down arrow. In either case, when you reach the item you want, press enter and that settings page will open.
  • =, that’s the equals sign: Calculator for performing calculations. Just enter your calculation and the result will be displayed. If, as I do, you are using a screen reader, the fastest way I have found to read the result is to press down arrow after entering my calculation. Note that you do not need to press enter after you have input your calculation. Also, again if using a screen reader, if you are comfortable with advanced screen reading techniques such as the JAWS Touch Cursor, NVDA Object Navigation or Narrator navigation commands, the result of the calculation and more can be read with these techniques. Last, after your result is displayed, you can press enter on the result and have it put on the Windows Clipboard.
  • !!, that is two presses of the exclamation mark key: History, quickly browse through your history with PowerToys Run with presses of down arrow.

Some Notes

PowerToys Run documentation indicates you can change the default shortcut for launching from Alt+Space.

According to PowerToys documentation, pressing tab is supposed to move you through search results and any buttons or context menus that exist. I am not finding anything being communicated by multiple screen readers as of now when using Tab. I still need to figure out if this is a case of the key simply not working or items taking focus not being communicated properly.

Leave a Comment