github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-16 14:39:31 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #14748] issue: TTS response not played in Voice Mode (Model: tts-1, Voice: nova, OpenAI API) #56018

New Issue
Closed
opened 2026-05-05 18:31:01 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-05 18:31:01 -05:00
Owner
Copy Link

Originally created by @Lyhtande on GitHub (Jun 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14748

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

v0.6.13

Ollama Version (if applicable)

No response

Operating System

Windows 11

Browser (if applicable)

Google 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 provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

When using Open WebUI in Voice Mode with the setting “Automatically read responses” enabled, I expect the model's text response to be converted to speech using the selected OpenAI TTS voice (tts-1, voice nova) and played back automatically, just as it works in normal mode.

Actual Behavior

In normal mode, the speech synthesis works correctly: the response is spoken using the selected voice.

However, in Voice Mode, even though the same setting is enabled, no audio is played.
The browser console repeatedly logs:
Audio for "[response text]" not yet available in the cache, re-queued...
This suggests the TTS response is never properly processed or played in Voice Mode.

Steps to Reproduce

  1. Start Open WebUI v0.6.13 locally
  2. Connect it to the OpenAI API (https://api.openai.com/v1)
  3. Enable TTS via the “Automatically read responses” toggle
  4. Set the voice to nova using model tts-1
  5. Switch to Voice Mode
  6. Ask any question (e.g. “What is a black hole?”)
  7. Observe: no audio playback, console shows repeated cache message

Logs & Screenshots

Audio for "[response text]" not yet available in the cache, re-queued...

Additional Information

WebUI version: 0.6.13 (latest)

Voice setting: nova (OpenAI TTS model tts-1)

Backend: OpenAI API (https://api.openai.com/v1)

Mode: Voice Mode

TTS Autoplay: Enabled

Browser: Google Chrome (latest)

Platform: Local installation (no Docker)

Originally created by @Lyhtande on GitHub (Jun 7, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/14748 ### 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 v0.6.13 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 ### Browser (if applicable) Google 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 **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior When using Open WebUI in Voice Mode with the setting “Automatically read responses” enabled, I expect the model's text response to be converted to speech using the selected OpenAI TTS voice (tts-1, voice nova) and played back automatically, just as it works in normal mode. ### Actual Behavior In normal mode, the speech synthesis works correctly: the response is spoken using the selected voice. However, in Voice Mode, even though the same setting is enabled, no audio is played. The browser console repeatedly logs: `Audio for "[response text]" not yet available in the cache, re-queued...` This suggests the TTS response is never properly processed or played in Voice Mode. ### Steps to Reproduce 1. Start Open WebUI v0.6.13 locally 2. Connect it to the OpenAI API (https://api.openai.com/v1) 3. Enable TTS via the “Automatically read responses” toggle 4. Set the voice to nova using model tts-1 5. Switch to Voice Mode 6. Ask any question (e.g. “What is a black hole?”) 7. Observe: no audio playback, console shows repeated cache message ### Logs & Screenshots `Audio for "[response text]" not yet available in the cache, re-queued...` ### Additional Information WebUI version: 0.6.13 (latest) Voice setting: nova (OpenAI TTS model tts-1) Backend: OpenAI API (https://api.openai.com/v1) Mode: Voice Mode TTS Autoplay: Enabled Browser: Google Chrome (latest) Platform: Local installation (no Docker)
GiteaMirror added the bug label 2026-05-05 18:31:01 -05:00
GiteaMirror commented 2026-05-05 18:31:07 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (Jun 7, 2025):

Unable to reproduce.

<!-- gh-comment-id:2952457378 --> @tjbck commented on GitHub (Jun 7, 2025): Unable to reproduce.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#56018
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?