Readers support Windows Report. We may earn a commission when you buy through our links.
Read our disclosure page to find out how you can help Windows Report support the editorial team. Learn more
In addition to the ability to switch between different search engines from the address bar, Firefox in Nightly has an AI feature that can automatically generate image descriptions in PDF documents when users manually add images. The feature isn’t perfect, but it’s promising.
Every major browser is integrating AI features and services, including chatbots. Google Chrome, Microsoft Edge, Opera and Brave are leading the way here. Google Chrome has announced and is testing new AI features based on Gemini, including history search, tab organization, tab comparison and more. Microsoft Edge has integrated the AI assistant Copilot into its sidebar. Opera has Aria and Brave has Leo.
Mozilla, which primarily depends on revenue from the Google search deal, has started giving its users access to various chatbots such as Gemini, ChatGPT, HuggingChat and Le Chat Mistral through its sidebar.
Not content with that, however, the company wants to provide “AI-generated alternative text for images inserted into PDFs” – an accessibility feature that meets the needs of the visually impaired and other users with learning disabilities.
Mozilla said the new AI feature will use a completely private AI model on the device. Firefox will add alt text to images in PDFs locally on the device. This feature will be available in Firefox’s built-in PDF editor and can be extended for general browsing with screen readers.
Mozilla wants to use AI based on small open source models. This approach requires only minimal computing resources.
We tested Firefox’s local alternative text generation feature for images in the PDF editor. Here’s how it works:
- . Open Firefox and a PDF in the browser.
- Press the >> Click the button in the toolbar and select “Alt image settings.“
- Download The Data carrier AI model and enable “Automatically generate alternative text”.
- Click “Close”.
- Add an image using the toolbar. The AI will generate alternative text.
- Edit the description if necessary and click Save.
- Review and save the changes to the PDF.
Although the feature is still in its early stages and uses a small model, it can generate descriptions that are sometimes accurate. See the attached examples for more details.
With this feature, Mozilla aims to improve accessibility and make inaccessible PDF images usable for those who need them most.
What do you think about Mozilla integrating AI into the Firefox PDF Editor to generate alt text for images? Let us know in the comments below.
Venkat, an experienced technology writer from India, specializes in discovering new web browser features and tech trends. His work bridges the gap between technology and its users and makes the digital world more accessible.
