Originally created by @RodolfoCastanheira on GitHub (Apr 10, 2025).
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
v0.6.2
### Ollama Version (if applicable)
_No response_
### Operating System
docker
### 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.
- [ ] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
Transcription of the audio.
### Actual Behavior
ERROR | open_webui.routers.audio:transcription:673 - 400: [ERROR: External: This model does not support the format you provided.] - {}
### Steps to Reproduce
Any audio message with the STT model as gpt-4o-transcribe (or mini) will fail.
### Logs & Screenshots
Full log of the error:
```
webui | 2025-04-10 18:19:48.718 | INFO | open_webui.routers.audio:transcription:626 - file.content_type: audio/wav - {}
webui | 2025-04-10 18:19:48.719 | INFO | open_webui.routers.audio:transcribe:470 - transcribe: /app/backend/data/cache/audio/transcriptions/d865d03d-3ad5-4718-be77-c716125cd334.wav - {}
webui | 2025-04-10 18:19:49.089 | DEBUG | urllib3.connectionpool:_new_conn:1049 - Starting new HTTPS connection (1): api.openai.com:443 - {}
webui | 2025-04-10 18:19:50.001 | DEBUG | urllib3.connectionpool:_make_request:544 - https://api.openai.com:443 "POST /v1/audio/transcriptions HTTP/1.1" 400 186 - {}
webui | 2025-04-10 18:19:50.001 | ERROR | open_webui.routers.audio:transcribe:525 - 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions - {}
webui | Traceback (most recent call last):
webui |
webui | File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
webui | self._bootstrap_inner()
webui | │ └ <function Thread._bootstrap_inner at 0xffffadbd4860>
webui | └ <WorkerThread(AnyIO worker thread, started 281469716853152)>
webui | File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
webui | self.run()
webui | │ └ <function WorkerThread.run at 0xffff54541120>
webui | └ <WorkerThread(AnyIO worker thread, started 281469716853152)>
webui | File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
webui | result = context.run(func, *args)
webui | │ │ │ └ ()
webui | │ │ └ functools.partial(<function transcription at 0xffff824453a0>, user=UserModel(id='f5121c84-0dc2-4480-a79a-d9bbe77fca6b', name=...
webui | │ └ <method 'run' of '_contextvars.Context' objects>
webui | └ <_contextvars.Context object at 0xffff4c6967c0>
webui |
webui | File "/app/backend/open_webui/routers/audio.py", line 661, in transcription
webui | data = transcribe(request, file_path)
webui | │ │ └ '/app/backend/data/cache/audio/transcriptions/d865d03d-3ad5-4718-be77-c716125cd334.wav'
webui | │ └ <starlette.requests.Request object at 0xffff4d4e6150>
webui | └ <function transcribe at 0xffff82445b20>
webui |
webui | > File "/app/backend/open_webui/routers/audio.py", line 515, in transcribe
webui | r.raise_for_status()
webui | │ └ <function Response.raise_for_status at 0xffffa9c5d760>
webui | └ <Response [400]>
webui |
webui | File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
webui | raise HTTPError(http_error_msg, response=self)
webui | │ │ └ <Response [400]>
webui | │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions'
webui | └ <class 'requests.exceptions.HTTPError'>
webui |
webui | requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions
webui | 2025-04-10 18:19:50.003 | ERROR | open_webui.routers.audio:transcription:665 - External: This model does not support the format you provided. - {}
webui | Traceback (most recent call last):
webui |
webui | File "/app/backend/open_webui/routers/audio.py", line 515, in transcribe
webui | r.raise_for_status()
webui | │ └ <function Response.raise_for_status at 0xffffa9c5d760>
webui | └ <Response [400]>
webui |
webui | File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
webui | raise HTTPError(http_error_msg, response=self)
webui | │ │ └ <Response [400]>
webui | │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions'
webui | └ <class 'requests.exceptions.HTTPError'>
webui |
webui | requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions
webui |
webui |
webui | During handling of the above exception, another exception occurred:
webui |
webui |
webui | Traceback (most recent call last):
webui |
webui | File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
webui | self._bootstrap_inner()
webui | │ └ <function Thread._bootstrap_inner at 0xffffadbd4860>
webui | └ <WorkerThread(AnyIO worker thread, started 281469716853152)>
webui | File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
webui | self.run()
webui | │ └ <function WorkerThread.run at 0xffff54541120>
webui | └ <WorkerThread(AnyIO worker thread, started 281469716853152)>
webui | File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
webui | result = context.run(func, *args)
webui | │ │ │ └ ()
webui | │ │ └ functools.partial(<function transcription at 0xffff824453a0>, user=UserModel(id='f5121c84-0dc2-4480-a79a-d9bbe77fca6b', name=...
webui | │ └ <method 'run' of '_contextvars.Context' objects>
webui | └ <_contextvars.Context object at 0xffff4c6967c0>
webui |
webui | > File "/app/backend/open_webui/routers/audio.py", line 661, in transcription
webui | data = transcribe(request, file_path)
webui | │ │ └ '/app/backend/data/cache/audio/transcriptions/d865d03d-3ad5-4718-be77-c716125cd334.wav'
webui | │ └ <starlette.requests.Request object at 0xffff4d4e6150>
webui | └ <function transcribe at 0xffff82445b20>
webui |
webui | File "/app/backend/open_webui/routers/audio.py", line 536, in transcribe
webui | raise Exception(detail if detail else "Open WebUI: Server Connection Error")
webui | │ └ 'External: This model does not support the format you provided.'
webui | └ 'External: This model does not support the format you provided.'
webui |
webui | Exception: External: This model does not support the format you provided.
webui | 2025-04-10 18:19:50.004 | ERROR | open_webui.routers.audio:transcription:673 - 400: [ERROR: External: This model does not support the format you provided.] - {}
webui | Traceback (most recent call last):
webui |
webui | File "/app/backend/open_webui/routers/audio.py", line 515, in transcribe
webui | r.raise_for_status()
webui | │ └ <function Response.raise_for_status at 0xffffa9c5d760>
webui | └ <Response [400]>
webui |
webui | File "/usr/local/lib/python3.11/site-packages/requests/models.py", line 1024, in raise_for_status
webui | raise HTTPError(http_error_msg, response=self)
webui | │ │ └ <Response [400]>
webui | │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions'
webui | └ <class 'requests.exceptions.HTTPError'>
webui |
webui | requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions
webui |
webui |
webui | During handling of the above exception, another exception occurred:
webui |
webui |
webui | Traceback (most recent call last):
webui |
webui | File "/app/backend/open_webui/routers/audio.py", line 661, in transcription
webui | data = transcribe(request, file_path)
webui | │ │ └ '/app/backend/data/cache/audio/transcriptions/d865d03d-3ad5-4718-be77-c716125cd334.wav'
webui | │ └ <starlette.requests.Request object at 0xffff4d4e6150>
webui | └ <function transcribe at 0xffff82445b20>
webui |
webui | File "/app/backend/open_webui/routers/audio.py", line 536, in transcribe
webui | raise Exception(detail if detail else "Open WebUI: Server Connection Error")
webui | │ └ 'External: This model does not support the format you provided.'
webui | └ 'External: This model does not support the format you provided.'
webui |
webui | Exception: External: This model does not support the format you provided.
webui |
webui |
webui | During handling of the above exception, another exception occurred:
webui |
webui |
webui | Traceback (most recent call last):
webui |
webui | File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
webui | self._bootstrap_inner()
webui | │ └ <function Thread._bootstrap_inner at 0xffffadbd4860>
webui | └ <WorkerThread(AnyIO worker thread, started 281469716853152)>
webui | File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
webui | self.run()
webui | │ └ <function WorkerThread.run at 0xffff54541120>
webui | └ <WorkerThread(AnyIO worker thread, started 281469716853152)>
webui | File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
webui | result = context.run(func, *args)
webui | │ │ │ └ ()
webui | │ │ └ functools.partial(<function transcription at 0xffff824453a0>, user=UserModel(id='f5121c84-0dc2-4480-a79a-d9bbe77fca6b', name=...
webui | │ └ <method 'run' of '_contextvars.Context' objects>
webui | └ <_contextvars.Context object at 0xffff4c6967c0>
webui |
webui | > File "/app/backend/open_webui/routers/audio.py", line 667, in transcription
webui | raise HTTPException(
webui | └ <class 'fastapi.exceptions.HTTPException'>
webui |
webui | fastapi.exceptions.HTTPException: 400: [ERROR: External: This model does not support the format you provided.]
```
### Additional Information
This appears to be solved by PR https://github.com/open-webui/open-webui/pull/12603
See this [bug from librechat](https://github.com/danny-avila/LibreChat/issues/6453) for more info.
GiteaMirror
added the bug label 2025-11-11 16:03:29 -06:00
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 @RodolfoCastanheira on GitHub (Apr 10, 2025).
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.2
Ollama Version (if applicable)
No response
Operating System
docker
Browser (if applicable)
chrome
Confirmation
README.md.Expected Behavior
Transcription of the audio.
Actual Behavior
ERROR | open_webui.routers.audio:transcription:673 - 400: [ERROR: External: This model does not support the format you provided.] - {}
Steps to Reproduce
Any audio message with the STT model as gpt-4o-transcribe (or mini) will fail.
Logs & Screenshots
Full log of the error:
Additional Information
This appears to be solved by PR https://github.com/open-webui/open-webui/pull/12603
See this bug from librechat for more info.
@tjbck commented on GitHub (Apr 10, 2025):
https://github.com/open-webui/open-webui/pull/12603 Merged!