langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

The process between speech and text #12333

New Issue
Closed
opened 2026-02-21 19:06:57 -05:00 by yindo · 4 comments
yindo commented 2026-02-21 19:06:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @infoBrainSys on GitHub (Mar 29, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
  • Please do not modify this template :) and fill in all the required fields.

Dify version

1.1.3

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

The actual processing time of four minutes of audio is only three To four seconds, but it takes about 10 minutes in the process of "Speech To Text." The back-end of both Xinference and dify does not output logs during the period, so it is not known what was done during the period, and the graphics card remains idle. What happened in the meantime?
Image

✔️ Expected Behavior

Understand what happens when you process speech

❌ Actual Behavior

No response

Originally created by @infoBrainSys on GitHub (Mar 29, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:) - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.1.3 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce The actual processing time of four minutes of audio is only three To four seconds, but it takes about 10 minutes in the process of "Speech To Text." The back-end of both Xinference and dify does not output logs during the period, so it is not known what was done during the period, and the graphics card remains idle. What happened in the meantime? ![Image](https://github.com/user-attachments/assets/ce5b7a88-881f-44a6-bde2-60619ac5c781) ### ✔️ Expected Behavior Understand what happens when you process speech ### ❌ Actual Behavior _No response_
yindo added the stt & tts label 2026-02-21 19:06:57 -05:00
yindo closed this issue 2026-02-21 19:06:57 -05:00
yindo commented 2026-02-21 19:06:57 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Mar 29, 2025):

I found a similar unsolved discussion that might be relevant to your issue: The API service that uses DIFY uses the streaming stream, but the result is that it waits for a long time to return at the same time, what is the reason for this? [1]. This discussion might provide some insights or lead to further troubleshooting steps.

Regarding your issue with the speech-to-text processing taking significantly longer than expected, there are a few known issues with Dify version 1.1.3 related to speech-to-text processing:

  1. ProviderNotSupportSpeechToTextError: This error indicates that the provider does not support speech-to-text functionality.
  2. NoAudioUploadedError: This error occurs when no audio is uploaded.
  3. AudioTooLargeError: This error is triggered when the audio size exceeds the allowed limit.
  4. UnsupportedAudioTypeError: This error occurs when the audio type is not allowed [2].

Since you mentioned that the GPU remains idle and there are no logs during the process, it might be helpful to check if the audio type and size are supported and if the provider you are using supports speech-to-text functionality. Additionally, enabling detailed logging might help diagnose the issue, although specific instructions for enabling logging in Dify were not found in the available information.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

@dosubot[bot] commented on GitHub (Mar 29, 2025): <!-- Answer --> I found a similar unsolved discussion that might be relevant to your issue: [The API service that uses DIFY uses the streaming stream, but the result is that it waits for a long time to return at the same time, what is the reason for this?](https://github.com/langgenius/dify/discussions/13700) <sup>[[1]](https://github.com/langgenius/dify/discussions/13700)</sup>. This discussion might provide some insights or lead to further troubleshooting steps. Regarding your issue with the speech-to-text processing taking significantly longer than expected, there are a few known issues with Dify version 1.1.3 related to speech-to-text processing: 1. **ProviderNotSupportSpeechToTextError**: This error indicates that the provider does not support speech-to-text functionality. 2. **NoAudioUploadedError**: This error occurs when no audio is uploaded. 3. **AudioTooLargeError**: This error is triggered when the audio size exceeds the allowed limit. 4. **UnsupportedAudioTypeError**: This error occurs when the audio type is not allowed <sup>[[2]](https://github.com/langgenius/dify/blob/main/api/controllers/web/error.py)</sup>. Since you mentioned that the GPU remains idle and there are no logs during the process, it might be helpful to check if the audio type and size are supported and if the provider you are using supports speech-to-text functionality. Additionally, enabling detailed logging might help diagnose the issue, although specific instructions for enabling logging in Dify were not found in the available information. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/db803a59-f944-43e7-ac1a-d7655cf1510b?feedback_type=other)</sup>
yindo commented 2026-02-21 19:06:57 -05:00
Author
Owner
Copy Link
Copy Source

@qqlww1987 commented on GitHub (Apr 2, 2025):

docker-plugin_daemon-1 100%

@qqlww1987 commented on GitHub (Apr 2, 2025): docker-plugin_daemon-1 100%
yindo commented 2026-02-21 19:06:58 -05:00
Author
Owner
Copy Link
Copy Source

@infoBrainSys commented on GitHub (Apr 2, 2025):

docker-plugin_daemon-1 100%

i don't understand. check logs of docker-plugin-daemon?

@infoBrainSys commented on GitHub (Apr 2, 2025): > docker-plugin_daemon-1 100% i don't understand. check logs of docker-plugin-daemon?
yindo commented 2026-02-21 19:06:58 -05:00
Author
Owner
Copy Link
Copy Source

@infoBrainSys commented on GitHub (Apr 2, 2025):

it's stop with no reason.
Image

@infoBrainSys commented on GitHub (Apr 2, 2025): it's stop with no reason. ![Image](https://github.com/user-attachments/assets/2e0d8387-71a8-4e5d-bdbd-eed6ee7cb062)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label stt & tts
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#12333
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?