[GH-ISSUE #13636] issue: STT with openAI and gpt-4o-mini-transcribe issue #103974

Closed
opened 2026-05-18 01:37:34 -05:00 by GiteaMirror · 8 comments
Owner

Originally created by @divemasterza on GitHub (May 7, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13636

Originally assigned to: @tjbck on GitHub.

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.6.7

Ollama Version (if applicable)

No response

Operating System

Ubuntu

Browser (if applicable)

Chrome latest

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 included the browser console logs.
  • I have included the Docker container logs.
  • I have listed steps to reproduce the bug in detail.

Expected Behavior

When setting openAI TTS and gpt-4o-mini-transcribe you expect to have the transcription

Actual Behavior

[ERROR: 400: [ERROR: External: Audio file might be corrupted or unsupported]] response

Steps to Reproduce

  1. Set openAI for STT
  2. Set model to gpt-4o-mini-transcribe
  3. voice prompt

Logs & Screenshots

2025-05-07 11:36:14.861 | INFO | open_webui.routers.audio:transcribe:507 - transcribe: /app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm - {}
May 07 13:36:15 2025-05-07 11:36:15.361 | INFO | open_webui.routers.audio:convert_audio_to_wav:98 - Converted /app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm to /app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm - {}
May 07 13:36:16 2025-05-07 11:36:16.833 | ERROR | open_webui.routers.audio:transcribe:572 - 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions - {}
May 07 13:36:16 Traceback (most recent call last):
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1030, in _bootstrap
May 07 13:36:16 self._bootstrap_inner()
May 07 13:36:16 │ └ <function Thread._bootstrap_inner at 0x7ef183022d40>
May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)>
May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1073, in _bootstrap_inner
May 07 13:36:16 self.run()
May 07 13:36:16 │ └ <function WorkerThread.run at 0x7ef0f94af060>
May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)>
May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 967, in run
May 07 13:36:16 result = context.run(func, *args)
May 07 13:36:16 │ │ │ └ ()
May 07 13:36:16 │ │ └ functools.partial(<function transcription at 0x7ef141784900>, user=UserModel(id='eba94052-ef1c-4cb3-9dae-bfcdf7b013af', name=...
May 07 13:36:16 │ └ <method 'run' of '_contextvars.Context' objects>
May 07 13:36:16 └ <_contextvars.Context object at 0x7ef0f9425e80>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 832, in transcription
May 07 13:36:16 data = transcribe(request, file_path)
May 07 13:36:16 │ │ └ '/app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm'
May 07 13:36:16 │ └ <starlette.requests.Request object at 0x7ef0d0615a90>
May 07 13:36:16 └ <function transcribe at 0x7ef141784d60>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 > File "/app/code/backend/open_webui/routers/audio.py", line 562, in transcribe
May 07 13:36:16 r.raise_for_status()
May 07 13:36:16 │ └ <function Response.raise_for_status at 0x7ef17fc5fec0>
May 07 13:36:16 └ <Response [400]>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status
May 07 13:36:16 raise HTTPError(http_error_msg, response=self)
May 07 13:36:16 │ │ └ <Response [400]>
May 07 13:36:16 │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions'
May 07 13:36:16 └ <class 'requests.exceptions.HTTPError'>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions
May 07 13:36:16 2025-05-07 11:36:16.834 | ERROR | open_webui.routers.audio:transcription:836 - External: Audio file might be corrupted or unsupported - {}
May 07 13:36:16 Traceback (most recent call last):
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 562, in transcribe
May 07 13:36:16 r.raise_for_status()
May 07 13:36:16 │ └ <function Response.raise_for_status at 0x7ef17fc5fec0>
May 07 13:36:16 └ <Response [400]>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status
May 07 13:36:16 raise HTTPError(http_error_msg, response=self)
May 07 13:36:16 │ │ └ <Response [400]>
May 07 13:36:16 │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions'
May 07 13:36:16 └ <class 'requests.exceptions.HTTPError'>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 During handling of the above exception, another exception occurred:
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 Traceback (most recent call last):
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1030, in _bootstrap
May 07 13:36:16 self._bootstrap_inner()
May 07 13:36:16 │ └ <function Thread._bootstrap_inner at 0x7ef183022d40>
May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)>
May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1073, in _bootstrap_inner
May 07 13:36:16 self.run()
May 07 13:36:16 │ └ <function WorkerThread.run at 0x7ef0f94af060>
May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)>
May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 967, in run
May 07 13:36:16 result = context.run(func, *args)
May 07 13:36:16 │ │ │ └ ()
May 07 13:36:16 │ │ └ functools.partial(<function transcription at 0x7ef141784900>, user=UserModel(id='eba94052-ef1c-4cb3-9dae-bfcdf7b013af', name=...
May 07 13:36:16 │ └ <method 'run' of '_contextvars.Context' objects>
May 07 13:36:16 └ <_contextvars.Context object at 0x7ef0f9425e80>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 > File "/app/code/backend/open_webui/routers/audio.py", line 832, in transcription
May 07 13:36:16 data = transcribe(request, file_path)
May 07 13:36:16 │ │ └ '/app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm'
May 07 13:36:16 │ └ <starlette.requests.Request object at 0x7ef0d0615a90>
May 07 13:36:16 └ <function transcribe at 0x7ef141784d60>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 583, in transcribe
May 07 13:36:16 raise Exception(detail if detail else "Open WebUI: Server Connection Error")
May 07 13:36:16 │ └ 'External: Audio file might be corrupted or unsupported'
May 07 13:36:16 └ 'External: Audio file might be corrupted or unsupported'
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 Exception: External: Audio file might be corrupted or unsupported
May 07 13:36:16 2025-05-07 11:36:16.835 | ERROR | open_webui.routers.audio:transcription:844 - 400: [ERROR: External: Audio file might be corrupted or unsupported] - {}
May 07 13:36:16 Traceback (most recent call last):
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 562, in transcribe
May 07 13:36:16 r.raise_for_status()
May 07 13:36:16 │ └ <function Response.raise_for_status at 0x7ef17fc5fec0>
May 07 13:36:16 └ <Response [400]>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status
May 07 13:36:16 raise HTTPError(http_error_msg, response=self)
May 07 13:36:16 │ │ └ <Response [400]>
May 07 13:36:16 │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions'
May 07 13:36:16 └ <class 'requests.exceptions.HTTPError'>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 During handling of the above exception, another exception occurred:
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 Traceback (most recent call last):
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 832, in transcription
May 07 13:36:16 data = transcribe(request, file_path)
May 07 13:36:16 │ │ └ '/app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm'
May 07 13:36:16 │ └ <starlette.requests.Request object at 0x7ef0d0615a90>
May 07 13:36:16 └ <function transcribe at 0x7ef141784d60>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 583, in transcribe
May 07 13:36:16 raise Exception(detail if detail else "Open WebUI: Server Connection Error")
May 07 13:36:16 │ └ 'External: Audio file might be corrupted or unsupported'
May 07 13:36:16 └ 'External: Audio file might be corrupted or unsupported'
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 Exception: External: Audio file might be corrupted or unsupported
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 During handling of the above exception, another exception occurred:
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 Traceback (most recent call last):
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1030, in _bootstrap
May 07 13:36:16 self._bootstrap_inner()
May 07 13:36:16 │ └ <function Thread._bootstrap_inner at 0x7ef183022d40>
May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)>
May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1073, in _bootstrap_inner
May 07 13:36:16 self.run()
May 07 13:36:16 │ └ <function WorkerThread.run at 0x7ef0f94af060>
May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)>
May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 967, in run
May 07 13:36:16 result = context.run(func, *args)
May 07 13:36:16 │ │ │ └ ()
May 07 13:36:16 │ │ └ functools.partial(<function transcription at 0x7ef141784900>, user=UserModel(id='eba94052-ef1c-4cb3-9dae-bfcdf7b013af', name=...
May 07 13:36:16 │ └ <method 'run' of '_contextvars.Context' objects>
May 07 13:36:16 └ <_contextvars.Context object at 0x7ef0f9425e80>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 > File "/app/code/backend/open_webui/routers/audio.py", line 838, in transcription
May 07 13:36:16 raise HTTPException(
May 07 13:36:16 └ <class 'fastapi.exceptions.HTTPException'>
May 07 13:36:16 2025-05-07T11:36:16Z
May 07 13:36:16 fastapi.exceptions.HTTPException: 400: [ERROR: External: Audio file might be corrupted or unsupported]

Additional Information

No response

Originally created by @divemasterza on GitHub (May 7, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/13636 Originally assigned to: @tjbck on GitHub. ### 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 0.6.7 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu ### Browser (if applicable) Chrome latest ### 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 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 When setting openAI TTS and gpt-4o-mini-transcribe you expect to have the transcription ### Actual Behavior [ERROR: 400: [ERROR: External: Audio file might be corrupted or unsupported]] response ### Steps to Reproduce 1. Set openAI for STT 2. Set model to gpt-4o-mini-transcribe 3. voice prompt ### Logs & Screenshots 2025-05-07 11:36:14.861 | INFO | open_webui.routers.audio:transcribe:507 - transcribe: /app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm - {} May 07 13:36:15 2025-05-07 11:36:15.361 | INFO | open_webui.routers.audio:convert_audio_to_wav:98 - Converted /app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm to /app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm - {} May 07 13:36:16 2025-05-07 11:36:16.833 | ERROR | open_webui.routers.audio:transcribe:572 - 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions - {} May 07 13:36:16 Traceback (most recent call last): May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1030, in _bootstrap May 07 13:36:16 self._bootstrap_inner() May 07 13:36:16 │ └ <function Thread._bootstrap_inner at 0x7ef183022d40> May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)> May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1073, in _bootstrap_inner May 07 13:36:16 self.run() May 07 13:36:16 │ └ <function WorkerThread.run at 0x7ef0f94af060> May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)> May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 967, in run May 07 13:36:16 result = context.run(func, *args) May 07 13:36:16 │ │ │ └ () May 07 13:36:16 │ │ └ functools.partial(<function transcription at 0x7ef141784900>, user=UserModel(id='eba94052-ef1c-4cb3-9dae-bfcdf7b013af', name=... May 07 13:36:16 │ └ <method 'run' of '_contextvars.Context' objects> May 07 13:36:16 └ <_contextvars.Context object at 0x7ef0f9425e80> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 832, in transcription May 07 13:36:16 data = transcribe(request, file_path) May 07 13:36:16 │ │ └ '/app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm' May 07 13:36:16 │ └ <starlette.requests.Request object at 0x7ef0d0615a90> May 07 13:36:16 └ <function transcribe at 0x7ef141784d60> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 > File "/app/code/backend/open_webui/routers/audio.py", line 562, in transcribe May 07 13:36:16 r.raise_for_status() May 07 13:36:16 │ └ <function Response.raise_for_status at 0x7ef17fc5fec0> May 07 13:36:16 └ <Response [400]> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status May 07 13:36:16 raise HTTPError(http_error_msg, response=self) May 07 13:36:16 │ │ └ <Response [400]> May 07 13:36:16 │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions' May 07 13:36:16 └ <class 'requests.exceptions.HTTPError'> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions May 07 13:36:16 2025-05-07 11:36:16.834 | ERROR | open_webui.routers.audio:transcription:836 - External: Audio file might be corrupted or unsupported - {} May 07 13:36:16 Traceback (most recent call last): May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 562, in transcribe May 07 13:36:16 r.raise_for_status() May 07 13:36:16 │ └ <function Response.raise_for_status at 0x7ef17fc5fec0> May 07 13:36:16 └ <Response [400]> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status May 07 13:36:16 raise HTTPError(http_error_msg, response=self) May 07 13:36:16 │ │ └ <Response [400]> May 07 13:36:16 │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions' May 07 13:36:16 └ <class 'requests.exceptions.HTTPError'> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 During handling of the above exception, another exception occurred: May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 Traceback (most recent call last): May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1030, in _bootstrap May 07 13:36:16 self._bootstrap_inner() May 07 13:36:16 │ └ <function Thread._bootstrap_inner at 0x7ef183022d40> May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)> May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1073, in _bootstrap_inner May 07 13:36:16 self.run() May 07 13:36:16 │ └ <function WorkerThread.run at 0x7ef0f94af060> May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)> May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 967, in run May 07 13:36:16 result = context.run(func, *args) May 07 13:36:16 │ │ │ └ () May 07 13:36:16 │ │ └ functools.partial(<function transcription at 0x7ef141784900>, user=UserModel(id='eba94052-ef1c-4cb3-9dae-bfcdf7b013af', name=... May 07 13:36:16 │ └ <method 'run' of '_contextvars.Context' objects> May 07 13:36:16 └ <_contextvars.Context object at 0x7ef0f9425e80> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 > File "/app/code/backend/open_webui/routers/audio.py", line 832, in transcription May 07 13:36:16 data = transcribe(request, file_path) May 07 13:36:16 │ │ └ '/app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm' May 07 13:36:16 │ └ <starlette.requests.Request object at 0x7ef0d0615a90> May 07 13:36:16 └ <function transcribe at 0x7ef141784d60> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 583, in transcribe May 07 13:36:16 raise Exception(detail if detail else "Open WebUI: Server Connection Error") May 07 13:36:16 │ └ 'External: Audio file might be corrupted or unsupported' May 07 13:36:16 └ 'External: Audio file might be corrupted or unsupported' May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 Exception: External: Audio file might be corrupted or unsupported May 07 13:36:16 2025-05-07 11:36:16.835 | ERROR | open_webui.routers.audio:transcription:844 - 400: [ERROR: External: Audio file might be corrupted or unsupported] - {} May 07 13:36:16 Traceback (most recent call last): May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 562, in transcribe May 07 13:36:16 r.raise_for_status() May 07 13:36:16 │ └ <function Response.raise_for_status at 0x7ef17fc5fec0> May 07 13:36:16 └ <Response [400]> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/requests/models.py", line 1024, in raise_for_status May 07 13:36:16 raise HTTPError(http_error_msg, response=self) May 07 13:36:16 │ │ └ <Response [400]> May 07 13:36:16 │ └ '400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions' May 07 13:36:16 └ <class 'requests.exceptions.HTTPError'> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 requests.exceptions.HTTPError: 400 Client Error: Bad Request for url: https://api.openai.com/v1/audio/transcriptions May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 During handling of the above exception, another exception occurred: May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 Traceback (most recent call last): May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 832, in transcription May 07 13:36:16 data = transcribe(request, file_path) May 07 13:36:16 │ │ └ '/app/data/cache/audio/transcriptions/d33864fb-bafa-4a15-a46a-398ed3c2e15e.webm' May 07 13:36:16 │ └ <starlette.requests.Request object at 0x7ef0d0615a90> May 07 13:36:16 └ <function transcribe at 0x7ef141784d60> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/app/code/backend/open_webui/routers/audio.py", line 583, in transcribe May 07 13:36:16 raise Exception(detail if detail else "Open WebUI: Server Connection Error") May 07 13:36:16 │ └ 'External: Audio file might be corrupted or unsupported' May 07 13:36:16 └ 'External: Audio file might be corrupted or unsupported' May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 Exception: External: Audio file might be corrupted or unsupported May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 During handling of the above exception, another exception occurred: May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 Traceback (most recent call last): May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1030, in _bootstrap May 07 13:36:16 self._bootstrap_inner() May 07 13:36:16 │ └ <function Thread._bootstrap_inner at 0x7ef183022d40> May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)> May 07 13:36:16 File "/usr/lib/python3.12/threading.py", line 1073, in _bootstrap_inner May 07 13:36:16 self.run() May 07 13:36:16 │ └ <function WorkerThread.run at 0x7ef0f94af060> May 07 13:36:16 └ <WorkerThread(AnyIO worker thread, started 139570439165632)> May 07 13:36:16 File "/app/code/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 967, in run May 07 13:36:16 result = context.run(func, *args) May 07 13:36:16 │ │ │ └ () May 07 13:36:16 │ │ └ functools.partial(<function transcription at 0x7ef141784900>, user=UserModel(id='eba94052-ef1c-4cb3-9dae-bfcdf7b013af', name=... May 07 13:36:16 │ └ <method 'run' of '_contextvars.Context' objects> May 07 13:36:16 └ <_contextvars.Context object at 0x7ef0f9425e80> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 > File "/app/code/backend/open_webui/routers/audio.py", line 838, in transcription May 07 13:36:16 raise HTTPException( May 07 13:36:16 └ <class 'fastapi.exceptions.HTTPException'> May 07 13:36:16 2025-05-07T11:36:16Z May 07 13:36:16 fastapi.exceptions.HTTPException: 400: [ERROR: External: Audio file might be corrupted or unsupported] ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-18 01:37:34 -05:00
Author
Owner

@Xi-Gong commented on GitHub (May 7, 2025):

Same problem here, v0.6.7 still can't fix the audio problem.

<!-- gh-comment-id:2858308782 --> @Xi-Gong commented on GitHub (May 7, 2025): Same problem here, v0.6.7 still can't fix the audio problem.
Author
Owner

@divemasterza commented on GitHub (May 7, 2025):

Same problem here, v0.6.7 still can't fix the audio problem.

it works if you switch to local Whisper and choose the small model (I am on a CPU only, so this is the only one that sorts of work)

OpenAI is superior, but broken in 0.6.7

<!-- gh-comment-id:2858667368 --> @divemasterza commented on GitHub (May 7, 2025): > Same problem here, v0.6.7 still can't fix the audio problem. it works if you switch to local Whisper and choose the small model (I am on a CPU only, so this is the only one that sorts of work) OpenAI is superior, but broken in 0.6.7
Author
Owner

@Xi-Gong commented on GitHub (May 7, 2025):

Same problem here, v0.6.7 still can't fix the audio problem.

it works if you switch to local Whisper and choose the small model (I am on a CPU only, so this is the only one that sorts of work)

OpenAI is superior, but broken in 0.6.7

I see...however I host open-webui on a 2-core web server, so OpenAI is my last bet, hope to fix soon.

<!-- gh-comment-id:2859203641 --> @Xi-Gong commented on GitHub (May 7, 2025): > > Same problem here, v0.6.7 still can't fix the audio problem. > > it works if you switch to local Whisper and choose the small model (I am on a CPU only, so this is the only one that sorts of work) > > OpenAI is superior, but broken in 0.6.7 I see...however I host open-webui on a 2-core web server, so OpenAI is my last bet, hope to fix soon.
Author
Owner

@tjbck commented on GitHub (May 7, 2025):

Investigating

<!-- gh-comment-id:2859755814 --> @tjbck commented on GitHub (May 7, 2025): Investigating
Author
Owner

@d1egoaz commented on GitHub (May 8, 2025):

This has been broken for me since version 0.6.6.

<!-- gh-comment-id:2863439491 --> @d1egoaz commented on GitHub (May 8, 2025): This has been broken for me since version 0.6.6.
Author
Owner

@tjbck commented on GitHub (May 8, 2025):

Might be addressed in dev, testing wanted here.

<!-- gh-comment-id:2864001192 --> @tjbck commented on GitHub (May 8, 2025): Might be addressed in dev, testing wanted here.
Author
Owner

@lnastjsj commented on GitHub (May 13, 2025):

0.6.9 Speech-to-Text Engine OpenAl "record voice"Report an error:[ERROR: 400: [ERROR: Open WebUI: Server Connection Error]]

<!-- gh-comment-id:2877985600 --> @lnastjsj commented on GitHub (May 13, 2025): 0.6.9 Speech-to-Text Engine OpenAl "record voice"Report an error:[ERROR: 400: [ERROR: Open WebUI: Server Connection Error]]
Author
Owner

@r0mdau commented on GitHub (May 14, 2025):

I've found a potential issue to solve this problem, at least for my use case: https://github.com/open-webui/open-webui/commit/bfa5550cc38dcdd2b95bdb605bb91451c60bac93

<!-- gh-comment-id:2881686522 --> @r0mdau commented on GitHub (May 14, 2025): I've found a potential issue to solve this problem, at least for my use case: https://github.com/open-webui/open-webui/commit/bfa5550cc38dcdd2b95bdb605bb91451c60bac93
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#103974