Vitechability
1.89K subscribers
33 files
169 links
this is the official channel of VI Techability
follow us on YouTube:
https://www.youtube.com/vitechability
facebook:
www.facebook.com/vitechability
Download Telegram
Pi_1.4_Join_VI_Techability_telegram_channel.apk
50.5 MB
pi AI Apk
watch our video to understand about this app.
https://youtu.be/km3AFrUJl8A
microsoft narrator have various natural neural voices, but what would happpen if we could use those voices with your favorite NVDA screen reader.
if you are interested then read the given article.
https://aryaniraula.com.np/how-to-use-microsoft-neural-voices-with-nvda-screenreader/
1👏1
Exciting news on the horizon for the blind and visually impaired community!
Get ready to experience a whole new level of independence with the upcoming integration of GPT-4-O, a powerful new model by OpenAI, into Be My Eyes! This incredible app, known for connecting you with live sighted volunteers for everyday tasks, is about to get even better.
Soon, Be My Eyes will leverage GPT-4-O to offer real-time scene descriptions through AI. Imagine giving your phone camera AI eyes that can describe your surroundings instantly! No more waiting for a volunteer's availability – GPT-4-O will be your on-demand AI assistant, ready to help whenever you need it.
This upcoming integration marks a revolutionary step forward in AI-powered assistance for the blind and visually impaired. It empowers us with greater independence and promises to open doors to a more accessible world.
To see how it works, check out this short video from Open AI showcasing the capabilities of GPT-4-O within Be My Eyes:
https://www.youtube.com/watch?v=KwNUJ69RbwY
VI Techability telegram channel
@vitechability
google lookout new update is out...
whats new:
Capture surroundings for a description in Images mode.
get guidance in taking selfie using the images mode.
note: inorder to save the photo, after you get description of the photo, click on the download button to save it in your internal storage / gallery.
@vitechability
a new mode has been introduced called find mode which helps Find nearby objects like cups, vehicles, and more.
Get improved text accuracy in Text, Documents, and Images mode
install google lookout:
https://play.google.com/store/apps/details?id=com.google.android.apps.accessibility.reveal&hl=en_US
join us for more updates
@vitechability
t.me/vitechability
Google TalkBack will use Gemini to describe images for blind people@vitechability
The company announced that Gemini Nano capabilities are coming to the company’s accessibility feature, TalkBack. This is a great example of a company using generative AI to open its software to more users.
Gemini Nano is the smallest version of Google’s LLM-based platform, designed to be run entirely on-device. That means it doesn't require a network connection to run. Here the program will be used to create aural descriptions of objects for low vision and blind users.
In the above pop-up, TalkBack refers to the article of clothing as, "A close-up of a black and white gingham dress. The dress is short, with a collar and long sleeves. It is tied at the waist with a big bow."
According to the company, TalkBack users encounter around 90 or so unlabeled images per day. Using LLMs, the system will be able to offer insight into content, potentially forgoing the need for someone to input that information manually.
“This update will help fill in missing information,” Android ecosystem president, Sameer Samat, noted, “whether it’s more details about what’s in a photo that family or friends sent or the style and cut of clothes when shopping online.”
join us
vitechability
t.me/vitechability
Be My Eyes is now on windows...
VI_Techability
With the Be My Eyes for Windows app, people who are blind or have low vision can now receive rapid, automated descriptions of screen elements, photographs and diagrams through AI-based natural language conversations, directly on their Windows 10/11 PC. By providing AI-powered descriptions of images and graphics, coupled with an interactive chatbot feature, the Be My Eyes app can be used for a wide variety of tasks, in a lot of different situations. Here's just a few ways in which it can be used: 
1. Describe Your Screen: whether it's an application interface or a web page layout, you can now get detailed descriptions through which you can now grasp any visual elements with ease.
2. Describe Local Images: From family photos to documents, you can now simply upload images to the Be My Eyes app  and receive comprehensive descriptions in return, in a matter of seconds.
3. Describe Online Images: Browsing the web becomes more inclusive as the Be My Eyes app seamlessly describes online images, ensuring no visual content goes undescribed.@vitechability
4. Help You Get Ready for Video Calls: By using a connected or built in camera, the Be My Eyes app can describe how you look to the camera, are you centered, or is the lighting ok, prior to a live video call.
And much more! Now it’s a conversation. Be My Eyes goes beyond mere description, allowing users to ask follow-up questions and delve deeper into the content being described.
download be my eyes:
https://www.microsoft.com/store/apps/9MSW46LTDWGF
join us for more interesting updates
@vitechability
t.me/vitechability
👍1
Be My Eyes Installer_join_VI_Techability_telegram_channel.exe
843.5 KB
this is be my eyes installer. use this to install be my eyes on those computer where microsoft store is not available.
VI Techability telegram channel
join us for more interesting updates
@vitechability
t.me/vitechability
One of the new features coming in NVDA 2024.2 is “Sound Split. This feature allows splitting NVDA sounds into one channel (e.g. left) while sounds from all other applications are directed to the other channel (e.g. right). VI Techability telegram channel.
The options for Sound Split are found in the “Audio” settings. Press NVDA+control+u to open this settings page directly. Alternatively, press NVDA+n to open the menu, then p for preferences, then enter to open settings. With Settings open, press control+tab to “Audio”. vitechability
There are eight options for sound split:
• Sound Split Disabled
• NVDA in both channels and applications in both channels
• NVDA on the left and applications on the right
• NVDA on the left and applications in both channels
• NVDA on the right and applications on the left
• NVDA on the right and applications in both channels
• NVDA in both channels and applications on the left
• NVDA in both channels and applications on the right
You can save how NVDA behaves (e.g. if you always want to have say NVDA on the left and applications on the right). You can also set which modes are available when using the new “Cycle Sound Split Mode” command. The command, NVDA+alt+s, cycles between any modes selected on this screen.
for more interesting updates join us
@vitechability
t.me/vitechability
WhatsApp:
https://whatsapp.com/channel/0029VaL5FekICVfoW6U7UI2I
facebook:
facebook.com/vitechability
Subject: Feature Ideas for Be My Eyes on Windows
Dear Be My Eyes Team,
I'm writing to express my sincere gratitude for bringing your award-winning "Be My Eyes" app to Windows. It's been a tremendous help in increasing my independence.
I'd like to propose a few features that could further enhance the app's functionality:
Adding Additional Pictures:
Currently, the app allows describing various elements like the screen, camera captures, and files. I believe the ability to attach multiple pictures within each "Describe" option would be incredibly beneficial.
Imagine wanting to compare two outfits for a meeting. With this feature, I could upload pictures of both and have the AI describe which one looks best overall. Similarly, before a video call, I could take a picture and ask if I'm properly visible. If not, I could adjust and attach another picture within the same chat session to see if the adjustments improved my visibility.
Text Navigation:
The ability to navigate text while reading AI image descriptions would also be a significant improvement. Currently, screen readers read the entire description aloud. However, navigation features like word-by-word or line-by-line movement would significantly enhance my ability to comprehend and efficiently process the information.
These features would greatly benefit visually impaired users like myself by increasing our independence and improving our experience with the Be My Eyes app.
Thank you for your time and consideration. I look forward to your feedback and the possibility of seeing these features implemented soon.
Sincerely,
VI Techability
prompt:
write an email to be my eyes team with the following point.
Subject: Feature Ideas for Be My Eyes on Windows
Body:
Start with appreciation (1-2 sentences):
• Express gratitude for bringing their award-winning "Be My Eyes" app to Windows. This has significantly improved my independence.
Suggest new features:

Adding Additional Pictures: Propose allowing users to attach multiple pictures within all existing "Describe" options on Be My Eyes. This could include:
◦ Describe My Screen
◦ Take Picture Using Built-in Camera
◦ Describe Picture from File Explorer
◦ Describe Clipboard

Mention potential benefits like comparing pictures for lighting/visibility or identifying specific details. For example, before a meeting or video call, I could take a picture of myself on camera and ask the AI if I'm properly visible. If not, I could then attach another picture within the same chat session, after making adjustments, and ask if I appear better in the second one.

Text navigation: Suggest the ability to navigate text while reading AI image descriptions (word-by-word, line-by-line, etc.). Explain how this improves comprehension and efficiency for visually impaired users.
Conclude with positivity:
• Briefly reiterate the value of these features for visually impaired users.
• Express hope for positive feedback and future implementation.
Hello friends,
You are all aware that Be My Eyes is now available on Windows, and it has been a valuable app for us, especially with its AI image description feature. However, the app could be even more useful if it allowed us to attach additional pictures within the same chat session and enabled text navigation for image descriptions, such as reading word by word or line by line with the help of a screen reader.
I have already suggested these features to the Be My Eyes team, but I believe that one email might not be enough. Therefore, let's conduct an experiment. I urge everyone in this channel to write an email to the Be My Eyes team, requesting the addition of these features to the Windows app.
To make this easier, I have provided a prompt you can use with ChatGPT, Gemini, or any other generative AI to write your email. If you prefer not to use AI, you can refer to the sample email I have provided and write a similar one, or simply copy and paste the sample email. The contact links and email addresses for Be My Eyes are given below.
Note: If you generate the email using the provided prompt with a generative AI, please make sure to check for any mistakes before sending it.
note2: please spread this message as much as you can.
Thank you for your support!
contact info:
web form:
https://support.bemyeyes.com/hc/en-us/requests/new
email:
support@bemyeyes.com
As discussed on Mozilla Connect, Firefox 130 will introduce an experimental new capability to automatically generate alt-text for images using a fully private on-device AI model. The feature will be available as part of Firefox’s built-in PDF editor, and our end goal is to make it available in general browsing for users with screen readers.
Why alt text?
Web pages have a fundamentally simple structure, with semantics that allow the browser to interpret the same content differently for different people based on their own needs and preferences. This is a big part of what we think makes the Web special, and what enables the browser to act as a user agent, responsible for making the Web work for people.
This is particularly useful for assistive technology such as screen readers, which are able to work alongside browser features to reduce obstacles for people to access and exchange information. For static web pages, this generally can be accomplished with very little interaction from the site, and this access has been enormously beneficial to many people.
But even for a simple static page there are certain types of information, like alternative text for images, that must be provided by the author to provide an understandable experience for people using assistive technology (as required by the spec). Unfortunately, many authors don’t do this: the Web Almanac reported in 2022 that nearly half of images were missing alt text.
Until recently it’s not been feasible for the browser to infer reasonably high quality alt text for images, without sending potentially sensitive data to a remote server. However, latest developments in AI have enabled this type of image analysis to happen efficiently, even on a CPU.
We are adding a feature within the PDF editor in Firefox Nightly to validate this approach. As we develop it further and learn from the deployment, our goal is to offer it for users who’d like to use it when browsing to help them better understand images which would otherwise be inaccessible.
Generating alt text with small open source models
We are using Transformer-based machine learning models to describe images. These models are getting good at describing the contents of the image, yet are compact enough to operate on devices with limited resources. While can’t outperform a large language model like GPT-4 Turbo with Vision, or LLaVA, they are sufficiently accurate to provide valuable insights on-device across a diversity of hardware.
Model architectures like BLIP or even VIT that were trained on datasets like COCO (Common Object In Context) or Flickr30k are good at identifying objects in an image. When combined with a text decoder like OpenAI’s GPT-2, they can produce alternative text with 200M or fewer parameters. Once quantized, these models can be under 200MB on disk, and run in a couple of seconds on a laptop – a big reduction compared to the gigabytes and resources an LLM requires. Example Output
The image below (pulled from the COCO dataset) is described by: FIREFOX
graphic: A person is standing in front of a cake with candles.
join us for more interesting updates
@vitechability
t.me/vitechability
WhatsApp:
https://whatsapp.com/channel/0029VaL5FekICVfoW6U7UI2I
facebook:
facebook.com/vitechability
1
What’s new with VoiceOver in iOS 18
Live Recognition, Detect text, people, doors, furniture and more by using the Live Recognition rotor.
VoiceOver Voice Rotor, The VoiceOver language rotor has become the voice rotor. Select any combination of voices, including those from the same language.
Audio Ducking, In VoiceOver > Audio settings, choose whether ducking is off, only active when speaking or always active. Control the level of the VoiceOver volume to be both louder and softer than media.
VoiceOver Tutorial, Learn how to use VoiceOver in a new tutorial that explains how to use VoiceOver commands to control iPhone.
Startup Haptic, VoiceOver uses a haptic to indicate it has started. It can be turned off in VoiceOver > Audio > Sounds & Haptics settings.
Delay before Selection, Control the amount of time before VoiceOver will select an item on the screen after touching the screen. Increasing this value can help reduce accidental touches moving focus.
New Language Support, VoiceOver now supports Lithuanian and Kazakh.
for more interesting updates
@vitechability
t.me/vitechability
WhatsApp:
https://whatsapp.com/channel/0029VaL5FekICVfoW6U7UI2I
facebook:
www.facebook.com/vitechability
good news for Bluetooth and other wireless headphone, speakers and earpods users.
there will be a new option in nvda 2024.2. this new option on the audio settings is “time to keep audio device awake after speech”.
This edit box specifies how long NVDA keeps the audio device awake after speech ends. This allows NVDA to avoid certain speech glitches like dropped parts of words. This can happen due to audio devices (especially Bluetooth and wireless devices) entering standby mode. This might also be helpful in other use cases, such as when running NVDA inside a virtual machine (e.g. Citrix Virtual Desktop), or on certain laptops.
join us for more interesting updates
@vitechability
t.me/vitechability
WhatsApp:
https://whatsapp.com/channel/0029VaL5FekICVfoW6U7UI2I
facebook:
www.facebook.com/vitechability
Audio
Andre Louis
this is the demo of meta glass.
join us for more interesting updates
@vitechability
t.me/vitechability
WhatsApp:
https://whatsapp.com/channel/0029VaL5FekICVfoW6U7UI2I
facebook:
www.facebook.com/vitechability
nvda_2024.2_VI_Techability_telegram_channel.exe
34.5 MB
There is a new feature called sound split. This allows splitting NVDA sounds into one channel (e.g. left) while sounds from all other applications are directed to the other channel (e.g. right).
There are new commands for modifying the synth settings ring, allowing users to jump to the first or last setting, and to increase or decrease the current setting in larger steps. There are also new quick navigation commands, allowing users to bind gestures to quickly jump between: paragraph, vertically aligned paragraph, same style text, different style text, menu item, toggle button, progress bar, figure, and math formula.
follow us for more updates
@vitechability
t.me/vitechability
WhatsApp:
https://whatsapp.com/channel/0029VaL5FekICVfoW6U7UI2I
facebook:
www.facebook.com/vitechability