feat: add Azure AI Speech STT provider

- Add Azure STT configuration variables for API key, region and locales
- Implement Azure STT transcription endpoint with 200MB file size limit
- Update Audio settings UI to include Azure STT configuration fields
- Handle Azure API responses and error cases consistently

backend/open_webui/config.py

@@ -2472,6 +2472,24 @@ AUDIO_STT_MODEL = PersistentConfig(
     os.getenv("AUDIO_STT_MODEL", ""),
 )
 
+AUDIO_STT_AZURE_API_KEY = PersistentConfig(
+    "AUDIO_STT_AZURE_API_KEY",
+    "audio.stt.azure.api_key",
+    os.getenv("AUDIO_STT_AZURE_API_KEY", ""),
+)
+
+AUDIO_STT_AZURE_REGION = PersistentConfig(
+    "AUDIO_STT_AZURE_REGION",
+    "audio.stt.azure.region",
+    os.getenv("AUDIO_STT_AZURE_REGION", ""),
+)
+
+AUDIO_STT_AZURE_LOCALES = PersistentConfig(
+    "AUDIO_STT_AZURE_LOCALES",
+    "audio.stt.azure.locales",
+    os.getenv("AUDIO_STT_AZURE_LOCALES", ""),
+)
+
 AUDIO_TTS_OPENAI_API_BASE_URL = PersistentConfig(
     "AUDIO_TTS_OPENAI_API_BASE_URL",
     "audio.tts.openai.api_base_url",

backend/open_webui/main.py

@@ -148,6 +148,9 @@ from open_webui.config import (
     AUDIO_STT_MODEL,
     AUDIO_STT_OPENAI_API_BASE_URL,
     AUDIO_STT_OPENAI_API_KEY,
+    AUDIO_STT_AZURE_API_KEY,
+    AUDIO_STT_AZURE_REGION,
+    AUDIO_STT_AZURE_LOCALES,
     AUDIO_TTS_API_KEY,
     AUDIO_TTS_ENGINE,
     AUDIO_TTS_MODEL,
@@ -778,6 +781,10 @@ app.state.config.STT_MODEL = AUDIO_STT_MODEL
 app.state.config.WHISPER_MODEL = WHISPER_MODEL
 app.state.config.DEEPGRAM_API_KEY = DEEPGRAM_API_KEY
 
+app.state.config.AUDIO_STT_AZURE_API_KEY = AUDIO_STT_AZURE_API_KEY
+app.state.config.AUDIO_STT_AZURE_REGION = AUDIO_STT_AZURE_REGION
+app.state.config.AUDIO_STT_AZURE_LOCALES = AUDIO_STT_AZURE_LOCALES
+
 app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
 app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
 app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE

backend/open_webui/routers/audio.py

@@ -50,6 +50,8 @@ router = APIRouter()
 # Constants
 MAX_FILE_SIZE_MB = 25
 MAX_FILE_SIZE = MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
+AZURE_MAX_FILE_SIZE_MB = 200
+AZURE_MAX_FILE_SIZE = AZURE_MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["AUDIO"])
@@ -141,6 +143,9 @@ class STTConfigForm(BaseModel):
     MODEL: str
     WHISPER_MODEL: str
     DEEPGRAM_API_KEY: str
+    AZURE_API_KEY: str
+    AZURE_REGION: str
+    AZURE_LOCALES: str
 
 
 class AudioConfigUpdateForm(BaseModel):
@@ -169,6 +174,9 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)):
             "MODEL": request.app.state.config.STT_MODEL,
             "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,
+            "AZURE_REGION": request.app.state.config.AUDIO_STT_AZURE_REGION,
+            "AZURE_LOCALES": request.app.state.config.AUDIO_STT_AZURE_LOCALES,
         },
     }
 
@@ -195,6 +203,9 @@ async def update_audio_config(
     request.app.state.config.STT_MODEL = form_data.stt.MODEL
     request.app.state.config.WHISPER_MODEL = form_data.stt.WHISPER_MODEL
     request.app.state.config.DEEPGRAM_API_KEY = form_data.stt.DEEPGRAM_API_KEY
+    request.app.state.config.AUDIO_STT_AZURE_API_KEY = form_data.stt.AZURE_API_KEY
+    request.app.state.config.AUDIO_STT_AZURE_REGION = form_data.stt.AZURE_REGION
+    request.app.state.config.AUDIO_STT_AZURE_LOCALES = form_data.stt.AZURE_LOCALES
 
     if request.app.state.config.STT_ENGINE == "":
         request.app.state.faster_whisper_model = set_faster_whisper_model(
@@ -220,6 +231,9 @@ async def update_audio_config(
             "MODEL": request.app.state.config.STT_MODEL,
             "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,
+            "AZURE_REGION": request.app.state.config.AUDIO_STT_AZURE_REGION,
+            "AZURE_LOCALES": request.app.state.config.AUDIO_STT_AZURE_LOCALES,
         },
     }
 
@@ -598,6 +612,107 @@ def transcribe(request: Request, file_path):
                     detail = f"External: {e}"
             raise Exception(detail if detail else "Open WebUI: Server Connection Error")
 
+    elif request.app.state.config.STT_ENGINE == "azure":
+        # Check file exists and size
+        if not os.path.exists(file_path):
+            raise HTTPException(
+                status_code=400,
+                detail="Audio file not found"
+            )
+
+        # Check file size (Azure has a larger limit of 200MB)
+        file_size = os.path.getsize(file_path)
+        if file_size > AZURE_MAX_FILE_SIZE:
+            raise HTTPException(
+                status_code=400,
+                detail=f"File size exceeds Azure's limit of {AZURE_MAX_FILE_SIZE_MB}MB",
+            )
+
+        api_key = request.app.state.config.AUDIO_STT_AZURE_API_KEY
+        region = request.app.state.config.AUDIO_STT_AZURE_REGION
+        locales = request.app.state.config.AUDIO_STT_AZURE_LOCALES
+
+        # IF NO LOCALES, USE DEFAULTS
+        if len(locales) < 2:
+            locales = ['en-US', 'es-ES', 'es-MX', 'fr-FR', 'hi-IN', 
+                       'it-IT','de-DE', 'en-GB', 'en-IN', 'ja-JP', 
+                       'ko-KR', 'pt-BR', 'zh-CN']
+            locales = ','.join(locales)
+
+
+        if not api_key or not region:
+            raise HTTPException(
+                status_code=400,
+                detail="Azure API key and region are required for Azure STT",
+            )
+
+        r = None
+        try:
+            # Prepare the request
+            data = {'definition': json.dumps({
+                                                "locales": locales.split(','),
+                                                "diarization": {"maxSpeakers": 3,"enabled": True}
+                                              } if locales else {}
+                                              )
+            }
+            url = f"https://{region}.api.cognitive.microsoft.com/speechtotext/transcriptions:transcribe?api-version=2024-11-15"
+            
+            # Use context manager to ensure file is properly closed
+            with open(file_path, 'rb') as audio_file:
+                r = requests.post(
+                    url=url,
+                    files={'audio': audio_file},
+                    data=data,
+                    headers={
+                        'Ocp-Apim-Subscription-Key': api_key,
+                    },
+                )
+
+            r.raise_for_status()
+            response = r.json()
+
+            # Extract transcript from response
+            if not response.get('combinedPhrases'):
+                raise ValueError("No transcription found in response")
+
+            # Get the full transcript from combinedPhrases
+            transcript = response['combinedPhrases'][0].get('text', '').strip()
+            if not transcript:
+                raise ValueError("Empty transcript in response")
+
+            data = {"text": transcript}
+
+            # Save transcript to json file (consistent with other providers)
+            transcript_file = f"{file_dir}/{id}.json"
+            with open(transcript_file, "w") as f:
+                json.dump(data, f)
+
+            log.debug(data)
+            return data
+
+        except (KeyError, IndexError, ValueError) as e:
+            log.exception("Error parsing Azure response")
+            raise HTTPException(
+                status_code=500,
+                detail=f"Failed to parse Azure response: {str(e)}",
+            )
+        except requests.exceptions.RequestException as e:
+            log.exception(e)
+            detail = None
+
+            try:
+                if r is not None and r.status_code != 200:
+                    res = r.json()
+                    if "error" in res:
+                        detail = f"External: {res['error'].get('message', '')}"
+            except Exception:
+                detail = f"External: {e}"
+
+            raise HTTPException(
+                status_code=getattr(r, 'status_code', 500) if r else 500,
+                detail=detail if detail else "Open WebUI: Server Connection Error",
+            )
+
 
 def compress_audio(file_path):
     if os.path.getsize(file_path) > MAX_FILE_SIZE:

src/lib/components/admin/Settings/Audio.svelte

@@ -39,6 +39,9 @@
 	let STT_ENGINE = '';
 	let STT_MODEL = '';
 	let STT_WHISPER_MODEL = '';
+	let STT_AZURE_API_KEY = '';
+	let STT_AZURE_REGION = '';
+	let STT_AZURE_LOCALES = '';
 	let STT_DEEPGRAM_API_KEY = '';
 
 	let STT_WHISPER_MODEL_LOADING = false;
@@ -103,12 +106,15 @@
 				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT
 			},
 			stt: {
-				OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
-				OPENAI_API_KEY: STT_OPENAI_API_KEY,
-				ENGINE: STT_ENGINE,
-				MODEL: STT_MODEL,
-				WHISPER_MODEL: STT_WHISPER_MODEL,
-				DEEPGRAM_API_KEY: STT_DEEPGRAM_API_KEY
+			    OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
+			    OPENAI_API_KEY: STT_OPENAI_API_KEY,
+			    ENGINE: STT_ENGINE,
+			    MODEL: STT_MODEL,
+			    WHISPER_MODEL: STT_WHISPER_MODEL,
+			    DEEPGRAM_API_KEY: STT_DEEPGRAM_API_KEY,
+			    AZURE_API_KEY: STT_AZURE_API_KEY,
+			    AZURE_REGION: STT_AZURE_REGION,
+			    AZURE_LOCALES: STT_AZURE_LOCALES
 			}
 		});
 
@@ -144,10 +150,13 @@
 
 			STT_OPENAI_API_BASE_URL = res.stt.OPENAI_API_BASE_URL;
 			STT_OPENAI_API_KEY = res.stt.OPENAI_API_KEY;
-
+			
 			STT_ENGINE = res.stt.ENGINE;
 			STT_MODEL = res.stt.MODEL;
 			STT_WHISPER_MODEL = res.stt.WHISPER_MODEL;
+			STT_AZURE_API_KEY = res.stt.AZURE_API_KEY;
+			STT_AZURE_REGION = res.stt.AZURE_REGION;
+			STT_AZURE_LOCALES = res.stt.AZURE_LOCALES;
 			STT_DEEPGRAM_API_KEY = res.stt.DEEPGRAM_API_KEY;
 		}
 
@@ -180,7 +189,8 @@
 							<option value="openai">OpenAI</option>
 							<option value="web">{$i18n.t('Web API')}</option>
 							<option value="deepgram">Deepgram</option>
-						</select>
+							<option value="azure">Azure AI Speech</option>
+							</select>
 					</div>
 				</div>
 
@@ -248,8 +258,35 @@
 							</a>
 						</div>
 					</div>
+				{:else if STT_ENGINE === 'azure'}
+				<div>
+				<div class="mt-1 flex gap-2 mb-1">
+				    <SensitiveInput placeholder={$i18n.t('API Key')} bind:value={STT_AZURE_API_KEY} required />
+				    <input
+				        class="flex-1 w-full rounded-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+				        placeholder={$i18n.t('Azure Region')}
+				        bind:value={STT_AZURE_REGION}
+				        required
+				    />
+				</div>
+				
+				<hr class="border-gray-100 dark:border-gray-850 my-2" />
+				
+				<div>
+				<div class=" mb-1.5 text-sm font-medium">{$i18n.t('Language Locales')}</div>
+				<div class="flex w-full">
+				    <div class="flex-1">
+				        <input
+				            class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+				            bind:value={STT_AZURE_LOCALES}
+				            placeholder={$i18n.t('e.g., en-US,ja-JP (leave blank for auto-detect)')}
+				        />
+				    </div>
+				</div>
+				</div>
+				</div>
 				{:else if STT_ENGINE === ''}
-					<div>
+				<div>
 						<div class=" mb-1.5 text-sm font-medium">{$i18n.t('STT Model')}</div>
 
 						<div class="flex w-full">