1038lab/ComfyUI-QwenTTS
1
0
Fork 0
mirror of https://github.com/1038lab/ComfyUI-QwenTTS.git synced 2026-11-04 23:37:45 +00:00
Code Issues 21 Projects Packages Wiki Activity

[GH-ISSUE #6] where is the advance workflows? when i use voice clone, it keep generate audio 2 minutes and 43 second. #5

New issue
Open
opened 2026-10-30 21:03:20 +00:00 by bsakaguchi · 3 comments
bsakaguchi commented 2026-10-30 21:03:20 +00:00
Owner
Copy link

Originally created by @LyonelleHansen on GitHub (Jan 25, 2026).
Original GitHub issue: https://github.com/1038lab/ComfyUI-QwenTTS/issues/6

i can't see the advance workflows. There only basic workflows for comfyui available.

When i use voice clone, it keep generate audio with duration 2 minutes and 43 seconds. No matter how long or short my text is. It only speak a few words at beginning of the text then it stop and start humming like wind noise or something.

I use macos 26, macbook pro m3 max.

Originally created by @LyonelleHansen on GitHub (Jan 25, 2026). Original GitHub issue: https://github.com/1038lab/ComfyUI-QwenTTS/issues/6 i can't see the advance workflows. There only basic workflows for comfyui available. When i use voice clone, it keep generate audio with duration 2 minutes and 43 seconds. No matter how long or short my text is. It only speak a few words at beginning of the text then it stop and start humming like wind noise or something. I use macos 26, macbook pro m3 max.
bsakaguchi commented 2026-10-30 21:03:21 +00:00
Author
Owner
Copy link

@nlienard commented on GitHub (Jan 31, 2026):

same issue, i ve a lot of long audio with long silence between speaking

<!-- gh-comment-id:3828743256 --> @nlienard commented on GitHub (Jan 31, 2026): same issue, i ve a lot of long audio with long silence between speaking
bsakaguchi commented 2026-10-30 21:03:21 +00:00
Author
Owner
Copy link

@nlienard commented on GitHub (Jan 31, 2026):

OK reduce max tokens to 256 and it is much better

<!-- gh-comment-id:3828753617 --> @nlienard commented on GitHub (Jan 31, 2026): OK reduce max tokens to 256 and it is much better
bsakaguchi commented 2026-10-30 21:03:22 +00:00
Author
Owner
Copy link

@rw-root commented on GitHub (Feb 23, 2026):

i fixed this with switching the text inputs,
the first text input is the one you need to put the text into that you want to hear,
the second input is the reference audio transcript

<!-- gh-comment-id:3944270205 --> @rw-root commented on GitHub (Feb 23, 2026): i fixed this with switching the text inputs, the first text input is the one you need to put the text into that you want to hear, the second input is the reference audio transcript
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
1038lab/ComfyUI-QwenTTS#5
No description provided.