[GH-ISSUE #13639] issue: OpenWeb-ui isn't automatically reading model output with my screen reader. #120291

Closed
opened 2026-05-20 21:54:14 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @Humanity121 on GitHub (May 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13639

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Git Clone

Open WebUI Version

latest

Ollama Version (if applicable)

latest

Operating System

windows 11

Browser (if applicable)

chrome

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have listed steps to reproduce the bug in detail.

Expected Behavior

I don't hav elogs as I'm not using docr and there's nothing to show you in the dev console.

Actual Behavior

Hello.
so I'm a totally blind guy and I've installed and setup open Web-ui.
I use the free nvda screen reader.
http://www.nvda-project.org
When I type into the chat box and hit enter text is not auatomatically read out with my screen reader. so I have to move out of the edit box and then up arrow and read the text manually.
The read allowed function sends it through sapi which is terrible.
There's some setting in Aria that I forget which should allow you to make any text coming in read automatically, or even better when it's finished generating if it could read the entire text auatomtically with nvda that would be great.
To test it where it works flawlessly, go to chatgpt.com with nvda installed and see how it works there.
Thank you.

Steps to Reproduce

TYPE INTO THE MODEL INPUT
press enter, see if you can hear anytthing read through nvda screen reader, it won't work.

Logs & Screenshots

nonge

Additional Information

No response

Originally created by @Humanity121 on GitHub (May 7, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/13639 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Git Clone ### Open WebUI Version latest ### Ollama Version (if applicable) latest ### Operating System windows 11 ### Browser (if applicable) chrome ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have listed steps to reproduce the bug in detail. ### Expected Behavior I don't hav elogs as I'm not using docr and there's nothing to show you in the dev console. ### Actual Behavior Hello. so I'm a totally blind guy and I've installed and setup open Web-ui. I use the free nvda screen reader. http://www.nvda-project.org When I type into the chat box and hit enter text is not auatomatically read out with my screen reader. so I have to move out of the edit box and then up arrow and read the text manually. The read allowed function sends it through sapi which is terrible. There's some setting in Aria that I forget which should allow you to make any text coming in read automatically, or even better when it's finished generating if it could read the entire text auatomtically with nvda that would be great. To test it where it works flawlessly, go to chatgpt.com with nvda installed and see how it works there. Thank you. ### Steps to Reproduce TYPE INTO THE MODEL INPUT press enter, see if you can hear anytthing read through nvda screen reader, it won't work. ### Logs & Screenshots nonge ### Additional Information _No response_
GiteaMirror added the buggood first issuehelp wanted labels 2026-05-20 21:54:26 -05:00
Author
Owner

@yo-nagase commented on GitHub (May 15, 2025):

I think www.nvda-project.org is not active anymore.

the website for the NVDA screen reader has changed. The former domain, nvda-project.org, is no longer active. The official website is now nvaccess.org, managed by NV Access, the organization responsible for developing NVDA.

I has been moved to the site below.
https://www.nvaccess.org/

<!-- gh-comment-id:2883764866 --> @yo-nagase commented on GitHub (May 15, 2025): I think www.nvda-project.org is not active anymore. > the website for the NVDA screen reader has changed. The former domain, [nvda-project.org](http://www.nvda-project.org/), is no longer active. The official website is now [nvaccess.org](https://www.nvaccess.org/), managed by NV Access, the organization responsible for developing NVDA. I has been moved to the site below. https://www.nvaccess.org/
Author
Owner

@yo-nagase commented on GitHub (May 16, 2025):

Since I found the way to implement this function, me and my collegue take this issue!

<!-- gh-comment-id:2885882561 --> @yo-nagase commented on GitHub (May 16, 2025): Since I found the way to implement this function, me and my collegue take this issue!
Author
Owner

@tts-yo-nagase commented on GitHub (May 16, 2025):

Thank you for your corresponse!

<!-- gh-comment-id:2886081202 --> @tts-yo-nagase commented on GitHub (May 16, 2025): Thank you for your corresponse!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#120291