refac

backend/open_webui/config.py

@@ -3947,6 +3947,19 @@ AUDIO_STT_SUPPORTED_CONTENT_TYPES = PersistentConfig(
     ],
 )
 
+AUDIO_STT_ALLOWED_EXTENSIONS = PersistentConfig(
+    'AUDIO_STT_ALLOWED_EXTENSIONS',
+    'audio.stt.allowed_extensions',
+    [
+        ext.strip()
+        for ext in os.environ.get(
+            'AUDIO_STT_ALLOWED_EXTENSIONS',
+            'mp3,wav,m4a,webm,ogg,flac,mp4,mpga,mpeg',
+        ).split(',')
+        if ext.strip()
+    ],
+)
+
 AUDIO_STT_AZURE_API_KEY = PersistentConfig(
     'AUDIO_STT_AZURE_API_KEY',
     'audio.stt.azure.api_key',

backend/open_webui/main.py

@@ -199,6 +199,7 @@ from open_webui.config import (
     AUDIO_STT_ENGINE,
     AUDIO_STT_MODEL,
     AUDIO_STT_SUPPORTED_CONTENT_TYPES,
+    AUDIO_STT_ALLOWED_EXTENSIONS,
     AUDIO_STT_OPENAI_API_BASE_URL,
     AUDIO_STT_OPENAI_API_KEY,
     AUDIO_STT_AZURE_API_KEY,
@@ -1289,6 +1290,7 @@ app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = IMAGES_EDIT_COMFYUI_WORKFL
 app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
 app.state.config.STT_MODEL = AUDIO_STT_MODEL
 app.state.config.STT_SUPPORTED_CONTENT_TYPES = AUDIO_STT_SUPPORTED_CONTENT_TYPES
+app.state.config.STT_ALLOWED_EXTENSIONS = AUDIO_STT_ALLOWED_EXTENSIONS
 
 app.state.config.STT_OPENAI_API_BASE_URL = AUDIO_STT_OPENAI_API_BASE_URL
 app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
@@ -2876,7 +2878,13 @@ async def serve_cache_file(
         raise HTTPException(status_code=404, detail='File not found')
     if not os.path.isfile(file_path):
         raise HTTPException(status_code=404, detail='File not found')
-    return FileResponse(file_path)
+
+    mime, _ = mimetypes.guess_type(file_path)
+    inline_safe = mime and mime.split('/', 1)[0] in {'image', 'audio', 'video'}
+    headers = {'X-Content-Type-Options': 'nosniff'}
+    if not inline_safe:
+        headers['Content-Disposition'] = f'attachment; filename="{os.path.basename(file_path)}"'
+    return FileResponse(file_path, headers=headers)
 
 
 def swagger_ui_html(*args, **kwargs):

backend/open_webui/routers/audio.py

@@ -178,6 +178,7 @@ class STTConfigForm(BaseModel):
     ENGINE: str
     MODEL: str
     SUPPORTED_CONTENT_TYPES: list[str] = []
+    ALLOWED_EXTENSIONS: list[str] = []
     WHISPER_MODEL: str
     DEEPGRAM_API_KEY: str
     AZURE_API_KEY: str
@@ -219,6 +220,7 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)):
             'ENGINE': request.app.state.config.STT_ENGINE,
             'MODEL': request.app.state.config.STT_MODEL,
             'SUPPORTED_CONTENT_TYPES': request.app.state.config.STT_SUPPORTED_CONTENT_TYPES,
+            'ALLOWED_EXTENSIONS': request.app.state.config.STT_ALLOWED_EXTENSIONS,
             'WHISPER_MODEL': request.app.state.config.WHISPER_MODEL,
             'DEEPGRAM_API_KEY': request.app.state.config.DEEPGRAM_API_KEY,
             'AZURE_API_KEY': request.app.state.config.AUDIO_STT_AZURE_API_KEY,
@@ -254,6 +256,7 @@ async def update_audio_config(request: Request, form_data: AudioConfigUpdateForm
     request.app.state.config.STT_ENGINE = form_data.stt.ENGINE
     request.app.state.config.STT_MODEL = form_data.stt.MODEL
     request.app.state.config.STT_SUPPORTED_CONTENT_TYPES = form_data.stt.SUPPORTED_CONTENT_TYPES
+    request.app.state.config.STT_ALLOWED_EXTENSIONS = form_data.stt.ALLOWED_EXTENSIONS
 
     request.app.state.config.WHISPER_MODEL = form_data.stt.WHISPER_MODEL
     request.app.state.config.DEEPGRAM_API_KEY = form_data.stt.DEEPGRAM_API_KEY
@@ -295,6 +298,7 @@ async def update_audio_config(request: Request, form_data: AudioConfigUpdateForm
             'ENGINE': request.app.state.config.STT_ENGINE,
             'MODEL': request.app.state.config.STT_MODEL,
             'SUPPORTED_CONTENT_TYPES': request.app.state.config.STT_SUPPORTED_CONTENT_TYPES,
+            'ALLOWED_EXTENSIONS': request.app.state.config.STT_ALLOWED_EXTENSIONS,
             'WHISPER_MODEL': request.app.state.config.WHISPER_MODEL,
             'DEEPGRAM_API_KEY': request.app.state.config.DEEPGRAM_API_KEY,
             'AZURE_API_KEY': request.app.state.config.AUDIO_STT_AZURE_API_KEY,
@@ -1242,7 +1246,14 @@ async def transcription(
 
     try:
         safe_name = os.path.basename(file.filename) if file.filename else ''
-        ext = safe_name.rsplit('.', 1)[-1] if '.' in safe_name else ''
+        ext = safe_name.rsplit('.', 1)[-1].lower() if '.' in safe_name else ''
+
+        allowed_extensions = getattr(request.app.state.config, 'STT_ALLOWED_EXTENSIONS', [])
+        if allowed_extensions and ext not in allowed_extensions:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail='Invalid audio file extension',
+            )
 
         id = uuid.uuid4()