Bug: Text-to-Speech Feature Reads Text in Markdown Format #2724

Closed
opened 2025-11-11 15:13:09 -06:00 by GiteaMirror · 1 comment
Owner

Originally created by @flefevre on GitHub (Nov 20, 2024).

Bug Report

Installation Method

docker 0.4.1

Environment

  • Open WebUI Version: [e.g., v0.3.11]
  • Ollama (if applicable): [e.g., v0.2.0, v0.1.32-rc1]

Confirmation:

  • [ x] I have read and followed all the instructions provided in the README.md.
  • [x ] I am on 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 provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.

Description:

The Text-to-Speech (TTS) feature has an issue when converting Markdown text to audio. It reads specific Markdown syntax, such as ### for headings, instead of ignoring these markers and focusing only on the textual content. This results in an unnatural and inconsistent user experience.

Steps to Reproduce:

  1. Provide a Markdown-formatted text to the TTS feature, for example:
    ### Example Heading
    Here is a paragraph.
    
  2. Trigger the audio conversion.
  3. Listen to the output.

Current Result:
The TTS reads:

"Hashtag hashtag hashtag Example Heading Here is a paragraph."

Expected Result:
The TTS should ignore Markdown syntax and read only the textual content:

"Example Heading. Here is a paragraph."

Impact:
This bug affects the clarity of audio conversion, making it less practical for professional or educational use.

Proposed Fix:
Implement a pre-processing step that:

  1. Strips or ignores Markdown syntax from the input text before passing it to the TTS engine.
  2. Ensures Markdown styling does not interfere with the readability of the content.

Labels: bug, text-to-speech, markdown

Originally created by @flefevre on GitHub (Nov 20, 2024). # Bug Report ## Installation Method docker 0.4.1 ## Environment - **Open WebUI Version:** [e.g., v0.3.11] - **Ollama (if applicable):** [e.g., v0.2.0, v0.1.32-rc1] **Confirmation:** - [ x] I have read and followed all the instructions provided in the README.md. - [x ] I am on 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 provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below. ## Description: The Text-to-Speech (TTS) feature has an issue when converting Markdown text to audio. It reads specific Markdown syntax, such as ### for headings, instead of ignoring these markers and focusing only on the textual content. This results in an unnatural and inconsistent user experience. **Steps to Reproduce**: 1. Provide a Markdown-formatted text to the TTS feature, for example: ```markdown ### Example Heading Here is a paragraph. ``` 2. Trigger the audio conversion. 3. Listen to the output. **Current Result**: The TTS reads: > "Hashtag hashtag hashtag Example Heading Here is a paragraph." **Expected Result**: The TTS should ignore Markdown syntax and read only the textual content: > "Example Heading. Here is a paragraph." **Impact**: This bug affects the clarity of audio conversion, making it less practical for professional or educational use. **Proposed Fix**: Implement a pre-processing step that: 1. Strips or ignores Markdown syntax from the input text before passing it to the TTS engine. 2. Ensures Markdown styling does not interfere with the readability of the content. **Labels**: `bug`, `text-to-speech`, `markdown`
Author
Owner

@flefevre commented on GitHub (Nov 20, 2024):

error

@flefevre commented on GitHub (Nov 20, 2024): error
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#2724