AI Content Describer for NVDA

This add-on makes it possible to obtain detailed descriptions for images, user interface controls, and other visually inaccessible content.

Leveraging the multimodal capabilities of advanced AI models and computer vision algorithms, we aim to deliver best-in-class content descriptions and increase independence overall. For more information about the underlying models, refer to the corresponding section of this document.

Features

Use case

There were a few primary motivations behind this project.

NVDA is capable of performing optical character recognition (OCR) out of the box, which is a game changer. If you are trying to get text out of an image or PDF document, this is what you're looking for.

However, OCR is only able to analyze data that might be text. It falls short at considering the context, objects and relationships conveyed in those images. And the internet is full of them. Logos, portraits, memes, icons, charts, diagrams, bar/line graphs... You name it. They're everywhere, and usually not in a format that screen reader users can interpret. Until recently, there has been an unwavering reliance on content authors providing alternative text descriptions. While this is still a must, it's difficult to change the fact that a high standard of quality happens to be the exception, not the rule.

Now, the possibilities are almost endless. You might:

Models

Follow the instructions provided below to get each of these working.

Getting started

Download the latest release of the add-on from this link. Click on the file on a computer with NVDA installed, and proceed with the installation as prompted.

As of version 2025.06.05, usage of GPT4 is free thanks to the generosity of the community behind PollinationsAI.

If you have the resources and interest in exploring additional models, you can always use your own API key and reduce requests to their servers. If you don't, feel free to skip down to the usage section of this document.

Follow the instructions below to obtain an API key from a supported provider.

Which model should I use?

We used to provide recommendations on the cheapest and highest quality options, but the landscape is changing so rapidly that it isn't possible to keep this up-to-date.

The short answer is that most of the state-of-the-art models have gotten to a point where they are accurate for most every-day use cases, so choose the provider that you are familiar with.

Most people want to strike a balance between accuracy and cost. The LLM arena leaderboard (specifically the vision category) measures correctness, while LLM pricing calculator outlines pricing.

Obtaining an API key from Open-AI:

  1. Go to open-AI's API key page
  2. If you don't yet have an account, create one. If you do, log in.
  3. On the API keys page, click to create a new secret key. Copy it to your clipboard.
  4. Fund the account with at least $1
  5. In the NVDA settings dialog, scroll down to the AI Content Describer category, then choose "manage models (alt+m)", select any of the OpenAI models (for example "GPT-4 omni") as the provider, tab into the API key field, and paste the key you just generated here.

At the time of this writing, Open-AI issues credits to new developer accounts that can be used for three months, after which they are lost. Following this period, you will have to purchase credits. Typical usage shouldn't ever exceed $5.00 per month. For a point of reference, the original version of this add-on was developed for slightly under a dollar. It is always possible to login to your OpenAI account and click on "usage" to get your quota.

Obtaining an API key from Google

  1. You will first need to create a Google workspace project by going to Google cloud console. Make sure you are logged in to your google account.
  2. Create a name between four and thirty characters, like "Gemini" or "NVDA add-on"
  3. Navigate to Google AI studio API keys page
  4. Click "create API key"
  5. In the NVDA settings dialog, scroll down to the AI Content Describer category, then choose "manage models (alt+m)", select "Google Gemini" as your provider, tab into the API key field, and paste the key you just generated here.

Obtaining an API key from Anthropic

  1. Login to the Anthropic console.
  2. Click on your profile -> API keys.
  3. Click Create Key.
  4. Enter a name for the key, like "AIContentDescriber", then click on "Create Key" and copy the value that shows up. This is what you will paste into the API key field under the Ai Content Describer category of the NVDA settings dialog -> manage models -> any Claude 4.x model (for example "Claude 4.6 Sonnet").
  5. If you haven't already, purchase at least $5 in credits under the anthropic plans page.

Obtaining an API key from Mistral

  1. Sign into or create a MistralAI account by going to the MistralAI login page.
  2. If you are creating or logging into an account for the first time, add a workspace as prompted, supplying a name and accepting the terms and conditions.
  3. Once logged in, select "API keys" from the menu.
  4. Click "create a new key", and copy it to your clipboard. This value is what you will paste into the API key field under the Ai Content Describer category of the NVDA settings dialog -> manage models -> Pixtral Large.
  5. Fund the account, if applicable.

Activating the VIVO BlueLM Vision Model via NVDA-CN

This service is made available free of charge through a partnership between VIVO (vivo.com.cn) and the NVDA Chinese Community (NVDACN). It provides high-quality multimodal recognition and is the recommended model for all users, especially those getting started.

To use this model, you only need a free NVDA-CN account.

  1. Create an Account: Go to the NVDA-CN registration page: https://nvdacn.com/admin/register.php.
  2. Verify Your Email: Check your inbox for a verification email and click the link inside to activate your account.
  3. Configure the Add-on:

You are now set up to use the VIVO model. For any account-related issues, you can contact the NVDA-CN team at support@nvdacn.com.

Setting up Ollama

This is currently the preferred option for a local setup.

Though the Ollama integration has been tested more extensively than llama.cpp, it is still less stable than calling out to an API and has been known to behave oddly under some configurations, up to and including crashes on machines that lack the required specifications. At bare minimum, when trying this out for the first time, save all documents and anything of importance before continuing in case this happens to you.

Start by ensuring that you are able to interact with your preferred vision-capable model using the commandline interface. The steps for doing so are as follows:

  1. Download the Ollama for Windows setup file from the Ollama downloads page.
  2. Run this setup file. It will handle grabbing all the dependencies that your machine will need.
  3. Locate the model you would like to use. A list can be found on ollama.com -> models -> vision, or here directly.
  4. Download and launch this model by opening a command prompt and typing ollama run [model_name], of course replacing "[model_name]" with the one you chose in step 3. For example, ollama run llama3.2-vision.
  5. Assuming the process completed successfully, you will be placed in an interactive shell wherein it is possible to type queries and get responses from the model, think a localized (and limited) ChatGPT. Test it out by asking something (anything) to see whether it works, then type "/bye" to exit this interface.
  6. Back in your console window, type ollama list. The first column will provide a name like "llama3.2-vision:latest".
  7. Navigate to AI Content Describer settings -> manage models -> Ollama. In the model name field, enter this value and click OK -> OK. You are all set! Switch to Ollama in the model submenu and it should work after some time.

Setting up llama.cpp

This provider is currently somewhat buggy, and your mileage may vary. It should really only be attempted by advanced users with an interest in running local self-hosted models, and the hardware to do so.

  1. Download llama.cpp. At the time of this writing, this pull request removes multimodal capabilities so you will want to use the last version with support for this. If you are running on an Nvidia graphics adapter with CUDA support, download these prebuilt binaries: llama-b2356-bin-win-cublas-cu12.2.0-x64.zip and cudart-llama-bin-win-cu12.2.0-x64.zip The steps for working with a different graphics adapter are out of scope, but can be found in the llama.cpp readme.
  2. Extract both of these files into the same folder.
  3. Locate the quantized formats of the models you'd like to use from Huggingface. For LLaVA 1.6 Vicuna 7B: llava-v1.6-vicuna-7b.Q4_K_M.gguf and mmproj-model-f16.gguf
  4. Put these files in the folder with the rest of the llama.cpp binaries.
  5. From a command prompt, run the llava.cpp server binary, passing the .gguf files for the model and multimodal projector (as follows): server.exe -m llava-v1.6-vicuna-7b.Q4_K_M.gguf --mmproj mmproj-model-f16.gguf
  6. In the NVDA settings dialog, scroll down to the AI Content Describer category, then choose "manage models (alt+m)", select "llama.cpp" as your provider, tab into the base URL field, and enter the endpoint shown in the console (defaults to "http://localhost:8080").
  7. Alternatively, you may omit some of these steps and run llama.cpp on a remote server with higher specs than your local machine, then enter that endpoint instead.

Setting up LiteLLM Proxy

LiteLLM Proxy provides a unified interface to access multiple AI models through a single endpoint, simplifying model management and allowing easy switching between providers.

  1. Set up a LiteLLM proxy server following the LiteLLM proxy documentation. You can run the proxy locally or use a remote server.
  2. If running locally, the quickest way to get started is: pip install 'litellm[proxy]' litellm --model gpt-4o This will start a proxy server at http://localhost:4000 that forwards requests to OpenAI's GPT-4o.
  3. For production use, create a config.yaml file to configure multiple models and authentication. See the LiteLLM configuration guide for details.
  4. In the NVDA settings dialog, scroll down to the AI Content Describer category, then choose "manage models (alt+m)", select "LiteLLM Proxy" as your provider.
  5. Enter your proxy server URL in the base URL field (e.g., "http://localhost:4000" for local or your remote server URL).
  6. If your proxy requires authentication, enter the API key in the API key field. If not, leave it blank.
  7. Click the "List models" button to fetch available models from your proxy, then select the model you want to use from the dropdown.
  8. Adjust other settings like prompt, max tokens, and timeout as needed, then click OK.

Note: The models available and their capabilities depend on your LiteLLM proxy configuration. Ensure your proxy is configured with vision-capable models for image description.

Setting up Seer

Seer runs PaliGemma2 on your own machine with no API key or cloud connection required. Note that this is a captioning-only model; prompts and follow-up questions are not supported.

  1. Install the Seer daemon. A one-command installer is provided for Windows (.bat) and Linux/macOS (.sh).
  2. In the NVDA settings dialog, navigate to the AI Content Describer category, choose "manage models (alt+m)", and select "Seer (requires installation)".
  3. The base URL defaults to http://127.0.0.1:11435. Leave it as-is unless you changed the daemon's port.
  4. Click OK. The daemon must be running before you attempt a description.

Usage

Five hotkeys are bound by default:

Three gestures are unbound:

Don't hesitate to customize these at any time from the input gestures dialog.

Following-up on a description

Sometimes, the response you get back from an AI is insufficient. Perhaps the image is low quality, incomplete, or includes unwanted details. Maybe you want to hone in on just a certain section or take a clearer photo without losing context. After receiving a description, you can press NVDA+alt+c, or select "Follow-up on previous description" from the AI Content Describer context menu (NVDA+shift+i). By default, the focus is set at the message field. To add an additional image, just keep the conversation window open and use the add-on as you normally would. When a picture is taken (be it from the camera, system control, screenshot, etc.) you will be asked if you want to attach it to the current session or start a new one.

Building the add-on

To create the add-on package from source, you will need:

Then open your terminal of choice:

git clone https://github.com/cartertemm/AI-content-describer.git cd AI-content-describer scons

After the scons command is finished executing, a *.nvda-addon file will be placed in the root of this repository ready for testing and release.

If you add additional strings that need to be translated, it is important to rebuild the .pot file like so:

scons pot

How to translate?

On a windows machine:

Contributions

All are highly appreciated and will be credited. The following people have worked on the addon.

Facing a problem? Submit it to the issue tracker

Have a suggestion for a new feature? Create a ticket for that as well, and we can talk about implementing it. Pull requests without associated issues will be reviewed, but are likely to take up more time for everyone, especially if I decide the new fix or functionality needs to work differently than what was proposed.

Translations are welcomed with open arms. The more people that can access this powerful technology, the better!

If you don't have Github, or prefer not to use it, you can shoot me an email - cartertemm (at) gmail (dot) com.

Thanks for the support!