I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Pip Install
Open WebUI Version
v0.6.25
Ollama Version (if applicable)
No response
Operating System
Debian 12
Browser (if applicable)
No response
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 provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
User can set the the ISO 639-1 language Whisper uses for STT.
Open-webui will include the language in the OpenAI request.
Actual Behavior
Since v0.6.23 Open-webui always request "en" instead of the language specified in user settings.
Using the environment configuration WHISPER_LANGUAGE to change the language, for example to “de,” works.
Originally created by @strizi9 on GitHub (Aug 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16884
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Pip Install
### Open WebUI Version
v0.6.25
### Ollama Version (if applicable)
_No response_
### Operating System
Debian 12
### Browser (if applicable)
_No response_
### 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 **provided every relevant configuration, setting, and environment variable used in my setup.**
- [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
- [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
- Start with the initial platform/version/OS and dependencies used,
- Specify exact install/launch/configure commands,
- List URLs visited, user input (incl. example values/emails/passwords if needed),
- Describe all options and toggles enabled or changed,
- Include any files or environmental changes,
- Identify the expected and actual result at each stage,
- Ensure any reasonably skilled user can follow and hit the same issue.
### Expected Behavior
User can set the the ISO 639-1 language Whisper uses for STT.
Open-webui will include the language in the OpenAI request.
### Actual Behavior
Since v0.6.23 Open-webui always request "en" instead of the language specified in user settings.
Using the environment configuration WHISPER_LANGUAGE to change the language, for example to “de,” works.
### Steps to Reproduce
1. Login to Open-webui
2. Settings
3. Audio
4. Language : de
### Logs & Screenshots
Before v0.6.23:
vllm[820132]: INFO 08-18 17:01:40 [logger.py:43] Received request transcribe-eb92482fd3f04c9880ef39f7637fdae8: prompt: '<|startoftranscript|><|de|><|transcribe|><|notimestamps|>', params: SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.0, top_p=1.0, top_k=0, min_p=0.0, seed=None, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=448, min_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None, extra_args=None), prompt_token_ids: None, prompt_embeds shape: None, lora_request: None, prompt_adapter_request: None.
With / after v0.6.23:
vllm[1983]: INFO 08-25 07:49:32 [logger.py:43] Received request transcribe-f2bc9db1fa3a4a6aa0f547ba3e1e088d: prompt: '<|startoftranscript|><|en|><|transcribe|><|notimestamps|>', params: SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.0, top_p=1.0, top_k=0, min_p=0.0, seed=None, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=448, min_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None, extra_args=None), prompt_token_ids: None, prompt_embeds shape: None, lora_request: None, prompt_adapter_request: None.
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-05-15 13:38:08 -05:00
I have the same issue. All stt generates English text. If I start with a Japanese voice I end up with an English translation in text instead of the actual Japanese text.
<!-- gh-comment-id:3240440052 -->
@SpiralCut commented on GitHub (Aug 31, 2025):
I have the same issue. All stt generates English text. If I start with a Japanese voice I end up with an English translation in text instead of the actual Japanese text.
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 @strizi9 on GitHub (Aug 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16884
Check Existing Issues
Installation Method
Pip Install
Open WebUI Version
v0.6.25
Ollama Version (if applicable)
No response
Operating System
Debian 12
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
User can set the the ISO 639-1 language Whisper uses for STT.
Open-webui will include the language in the OpenAI request.
Actual Behavior
Since v0.6.23 Open-webui always request "en" instead of the language specified in user settings.
Using the environment configuration WHISPER_LANGUAGE to change the language, for example to “de,” works.
Steps to Reproduce
Logs & Screenshots
Before v0.6.23:
vllm[820132]: INFO 08-18 17:01:40 [logger.py:43] Received request transcribe-eb92482fd3f04c9880ef39f7637fdae8: prompt: '<|startoftranscript|><|de|><|transcribe|><|notimestamps|>', params: SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.0, top_p=1.0, top_k=0, min_p=0.0, seed=None, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=448, min_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None, extra_args=None), prompt_token_ids: None, prompt_embeds shape: None, lora_request: None, prompt_adapter_request: None.
With / after v0.6.23:
vllm[1983]: INFO 08-25 07:49:32 [logger.py:43] Received request transcribe-f2bc9db1fa3a4a6aa0f547ba3e1e088d: prompt: '<|startoftranscript|><|en|><|transcribe|><|notimestamps|>', params: SamplingParams(n=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.0, top_p=1.0, top_k=0, min_p=0.0, seed=None, stop=[], stop_token_ids=[], bad_words=[], include_stop_str_in_output=False, ignore_eos=False, max_tokens=448, min_tokens=0, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True, truncate_prompt_tokens=None, guided_decoding=None, extra_args=None), prompt_token_ids: None, prompt_embeds shape: None, lora_request: None, prompt_adapter_request: None.
Additional Information
No response
@SpiralCut commented on GitHub (Aug 31, 2025):
I have the same issue. All stt generates English text. If I start with a Japanese voice I end up with an English translation in text instead of the actual Japanese text.