I have searched the existing issues and discussions.
Installation Method
Other
Open WebUI Version
v0.5.18
Ollama Version (if applicable)
No response
Operating System
Kubernates
Browser (if applicable)
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 checked the browser console logs.
I have checked the Docker container logs.
I have listed steps to reproduce the bug in detail.
Expected Behavior
Voice chat works properly
Actual Behavior
[ERROR: 400: [ERROR: Open WebUI: Server Connection Error]]
Steps to Reproduce
setup whisper 1
Record audio
whaiting error
Logs & Screenshots
ERROR [open_webui.routers.audio] 400: [ERROR: Open WebUI: Server Connection Error]
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 582, in transcription
data = transcribe(request, file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/audio.py", line 522, in transcribe
raise Exception(detail if detail else "Open WebUI: Server Connection Error")
Exception: Open WebUI: Server Connection Error
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 588, in transcription
raise HTTPException(
fastapi.exceptions.HTTPException: 400: [ERROR: Open WebUI: Server Connection Error]
[32mINFO[0m: 10.5.32.114:0 - "[1mPOST /api/v1/audio/transcriptions HTTP/1.1[0m" [31m400 Bad Request[0m
[32mINFO[0m: connection closed
WARNI [python_multipart.multipart] Skipping data after last boundary
INFO [open_webui.routers.audio] file.content_type: audio/wav
transcribe /app/backend/data/cache/audio/transcriptions/86e82464-3651-469f-93d8-e6fe6c2ccbd8.wav
[32mINFO[0m: ('172.27.126.151', 0) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket" [accepted]
[32mINFO[0m: connection open
ERROR [open_webui.routers.audio] 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
ERROR [open_webui.routers.audio] Open WebUI: Server Connection Error
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 582, in transcription
data = transcribe(request, file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/audio.py", line 522, in transcribe
raise Exception(detail if detail else "Open WebUI: Server Connection Error")
Exception: Open WebUI: Server Connection Error
ERROR [open_webui.routers.audio] 400: [ERROR: Open WebUI: Server Connection Error]
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 582, in transcription
data = transcribe(request, file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/audio.py", line 522, in transcribe
raise Exception(detail if detail else "Open WebUI: Server Connection Error")
Exception: Open WebUI: Server Connection Error
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 588, in transcription
raise HTTPException(
fastapi.exceptions.HTTPException: 400: [ERROR: Open WebUI: Server Connection Error]
[32mINFO[0m: 10.5.32.114:0 - "[1mPOST /api/v1/audio/transcriptions HTTP/1.1[0m" [31m400 Bad Request[0m
Additional Information
Originally created by @YuriyGavrilov on GitHub (Mar 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11363
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
### Installation Method
Other
### Open WebUI Version
v0.5.18
### Ollama Version (if applicable)
_No response_
### Operating System
Kubernates
### Browser (if applicable)
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 checked the browser console logs.
- [x] I have checked the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
Voice chat works properly
### Actual Behavior
[ERROR: 400: [ERROR: Open WebUI: Server Connection Error]]
### Steps to Reproduce
1. setup whisper 1
2. Record audio
3. whaiting error
### Logs & Screenshots
```
ERROR [open_webui.routers.audio] 400: [ERROR: Open WebUI: Server Connection Error]
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 582, in transcription
data = transcribe(request, file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/audio.py", line 522, in transcribe
raise Exception(detail if detail else "Open WebUI: Server Connection Error")
Exception: Open WebUI: Server Connection Error
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 588, in transcription
raise HTTPException(
fastapi.exceptions.HTTPException: 400: [ERROR: Open WebUI: Server Connection Error]
[32mINFO[0m: 10.5.32.114:0 - "[1mPOST /api/v1/audio/transcriptions HTTP/1.1[0m" [31m400 Bad Request[0m
[32mINFO[0m: connection closed
WARNI [python_multipart.multipart] Skipping data after last boundary
INFO [open_webui.routers.audio] file.content_type: audio/wav
transcribe /app/backend/data/cache/audio/transcriptions/86e82464-3651-469f-93d8-e6fe6c2ccbd8.wav
[32mINFO[0m: ('172.27.126.151', 0) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket" [accepted]
[32mINFO[0m: connection open
ERROR [open_webui.routers.audio] 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
ERROR [open_webui.routers.audio] Open WebUI: Server Connection Error
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 582, in transcription
data = transcribe(request, file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/audio.py", line 522, in transcribe
raise Exception(detail if detail else "Open WebUI: Server Connection Error")
Exception: Open WebUI: Server Connection Error
ERROR [open_webui.routers.audio] 400: [ERROR: Open WebUI: Server Connection Error]
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 501, in transcribe
r.raise_for_status()
File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 582, in transcription
data = transcribe(request, file_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/backend/open_webui/routers/audio.py", line 522, in transcribe
raise Exception(detail if detail else "Open WebUI: Server Connection Error")
Exception: Open WebUI: Server Connection Error
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/app/backend/open_webui/routers/audio.py", line 588, in transcription
raise HTTPException(
fastapi.exceptions.HTTPException: 400: [ERROR: Open WebUI: Server Connection Error]
[32mINFO[0m: 10.5.32.114:0 - "[1mPOST /api/v1/audio/transcriptions HTTP/1.1[0m" [31m400 Bad Request[0m
```
### Additional Information
<!-- Failed to upload "image.png" -->
GiteaMirror
added the bug label 2026-05-25 03:18:18 -05:00
I have the same issue.
I downloaded the generated file and tried to upload it via Postman, but I got this error: "Cannot extract audio duration. Invalid file or format."
After that, I tried to upload a simple WAV file with audio, and it was successfully recognized.
I use a proxyapi for accessing the OpenAI API, so I can't check this issue on the native OpenAI API.\
UPD
On another API provider, the problem persists as well.
<!-- gh-comment-id:2708350002 -->
@FedorRasputin commented on GitHub (Mar 8, 2025):
I have the same issue.
I downloaded the generated file and tried to upload it via Postman, but I got this error: "Cannot extract audio duration. Invalid file or format."
After that, I tried to upload a simple WAV file with audio, and it was successfully recognized.
I use a proxyapi for accessing the OpenAI API, so I can't check this issue on the native OpenAI API.\
UPD
On another API provider, the problem persists as well.
@michaelmarziani commented on GitHub (Mar 12, 2025):
@YuriyGavrilov I'm unable to reproduce this error on my setup. I use local whisper and I've picked a different model, as you can see in my setup below.
Please upload a screenshot of your audio settings, as I think something looks odd with the error you received:
@FedorRasputin Please post the stack trace from the console for your error.
<!-- gh-comment-id:2716761196 -->
@michaelmarziani commented on GitHub (Mar 12, 2025):
@YuriyGavrilov I'm unable to reproduce this error on my setup. I use local whisper and I've picked a different model, as you can see in my setup below.
Please upload a screenshot of your audio settings, as I think something looks odd with the error you received:
> 400 Client Error: Bad Request for url: https://XXXXXXXXXX/openai/v1/audio/transcriptions
@FedorRasputin Please post the stack trace from the console for your error.
A bad request in this context means that the server is rejecting this transcription request. Unfortunately there isn't enough detail in the error message to know why.
To troubleshoot, I would try different servers in my configuration. If this works, then you know it's a problem with this specific server, if you test a few servers and none of them work, either they all are having an issue or there might be a problem in the request code in OWUI.
Good luck!
<!-- gh-comment-id:2721235337 -->
@michaelmarziani commented on GitHub (Mar 13, 2025):
Hi @FedorRasputin, the way I read this, the error is here:
> openwebui-1 | requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.proxyapi.ru/openai/v1/audio/transcriptions
A bad request in this context means that the server is rejecting this transcription request. Unfortunately there isn't enough detail in the error message to know why.
To troubleshoot, I would try different servers in my configuration. If this works, then you know it's a problem with this specific server, if you test a few servers and none of them work, either they all are having an issue or there might be a problem in the request code in OWUI.
Good luck!
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @YuriyGavrilov on GitHub (Mar 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11363
Check Existing Issues
Installation Method
Other
Open WebUI Version
v0.5.18
Ollama Version (if applicable)
No response
Operating System
Kubernates
Browser (if applicable)
Chrome
Confirmation
README.md.Expected Behavior
Voice chat works properly
Actual Behavior
[ERROR: 400: [ERROR: Open WebUI: Server Connection Error]]
Steps to Reproduce
Logs & Screenshots
Additional Information
@FedorRasputin commented on GitHub (Mar 8, 2025):
I have the same issue.
I downloaded the generated file and tried to upload it via Postman, but I got this error: "Cannot extract audio duration. Invalid file or format."
After that, I tried to upload a simple WAV file with audio, and it was successfully recognized.
I use a proxyapi for accessing the OpenAI API, so I can't check this issue on the native OpenAI API.\
UPD
On another API provider, the problem persists as well.
@michaelmarziani commented on GitHub (Mar 12, 2025):
@YuriyGavrilov I'm unable to reproduce this error on my setup. I use local whisper and I've picked a different model, as you can see in my setup below.
Please upload a screenshot of your audio settings, as I think something looks odd with the error you received:
@FedorRasputin Please post the stack trace from the console for your error.
@FedorRasputin commented on GitHub (Mar 12, 2025):
@michaelmarziani Hello.
My settings:
Stack trace from console:
@michaelmarziani commented on GitHub (Mar 13, 2025):
Hi @FedorRasputin, the way I read this, the error is here:
A bad request in this context means that the server is rejecting this transcription request. Unfortunately there isn't enough detail in the error message to know why.
To troubleshoot, I would try different servers in my configuration. If this works, then you know it's a problem with this specific server, if you test a few servers and none of them work, either they all are having an issue or there might be a problem in the request code in OWUI.
Good luck!