mirror of
https://github.com/open-webui/open-webui.git
synced 2026-06-05 16:28:32 -05:00
[GH-ISSUE #18237] feat: have TTS Engine calls occure while response text is still appearing #73145
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#73145
Reference in New Issue
Block a user
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?
Originally created by @RetroZelda on GitHub (Oct 11, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18237
Check Existing Issues
Problem Description
im using chatterbox for TTS and the delay from the text response appearing to when the TTS plays back is very long. It seems like it waits for the entire promt to finish before calling the api to generate the audio.
Desired Solution you'd like
I think it could speed things up greatly if the "response splitting" setting in
admin/settings/audiocould start splitting the responses and sending them off as the response is generated.An example is right now I have it set to "Punctuation" and it will wait for the entire promt to finish, but instead it could see that a period, question mark, etc was output and to then send off that sentence to the TTS engine to begin generating the response.
Alternatives Considered
No response
Additional Context
No response
@tjbck commented on GitHub (Oct 11, 2025):
Implemented with voice mode.