refac

backend/open_webui/apps/audio/main.py

@@ -161,7 +161,9 @@ async def update_audio_config(
     app.state.config.TTS_VOICE = form_data.tts.VOICE
     app.state.config.TTS_SPLIT_ON = form_data.tts.SPLIT_ON
     app.state.config.TTS_AZURE_SPEECH_REGION = form_data.tts.AZURE_SPEECH_REGION
-    app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = form_data.tts.AZURE_SPEECH_OUTPUT_FORMAT
+    app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = (
+        form_data.tts.AZURE_SPEECH_OUTPUT_FORMAT
+    )
 
     app.state.config.STT_OPENAI_API_BASE_URL = form_data.stt.OPENAI_API_BASE_URL
     app.state.config.STT_OPENAI_API_KEY = form_data.stt.OPENAI_API_KEY
@@ -314,7 +316,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                 detail=error_detail,
             )
 
-    elif app.state.config.TTS_ENGINE == "azurespeechservice":
+    elif app.state.config.TTS_ENGINE == "azure":
         payload = None
         try:
             payload = json.loads(body.decode("utf-8"))
@@ -329,9 +331,9 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         url = f"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1"
 
         headers = {
-            'Ocp-Apim-Subscription-Key': app.state.config.TTS_API_KEY,
-            'Content-Type': 'application/ssml+xml',
-            'X-Microsoft-OutputFormat': output_format
+            "Ocp-Apim-Subscription-Key": app.state.config.TTS_API_KEY,
+            "Content-Type": "application/ssml+xml",
+            "X-Microsoft-OutputFormat": output_format,
         }
 
         data = f"""<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="{locale}">
@@ -347,9 +349,8 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         else:
             log.error(f"Error synthesizing speech - {response.reason}")
             raise HTTPException(
-                status_code=500,
-                detail=f"Error synthesizing speech - {response.reason}")
-
+                status_code=500, detail=f"Error synthesizing speech - {response.reason}"
+            )
 
 
 @app.post("/transcriptions")
@@ -528,23 +529,22 @@ def get_available_voices() -> dict:
         except Exception:
             # Avoided @lru_cache with exception
             pass
-    elif app.state.config.TTS_ENGINE == "azurespeechservice":
+    elif app.state.config.TTS_ENGINE == "azure":
         try:
             region = app.state.config.TTS_AZURE_SPEECH_REGION
             url = f"https://{region}.tts.speech.microsoft.com/cognitiveservices/voices/list"
-            headers = {
-                'Ocp-Apim-Subscription-Key': app.state.config.TTS_API_KEY
-            }
+            headers = {"Ocp-Apim-Subscription-Key": app.state.config.TTS_API_KEY}
 
             response = requests.get(url, headers=headers)
             response.raise_for_status()
             voices = response.json()
             for voice in voices:
-                ret[voice['ShortName']] = f"{voice['DisplayName']} ({voice['ShortName']})"
+                ret[voice["ShortName"]] = (
+                    f"{voice['DisplayName']} ({voice['ShortName']})"
+                )
         except requests.RequestException as e:
             log.error(f"Error fetching voices: {str(e)}")
 
-
     return ret
 
 

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

@@ -91,7 +91,7 @@
 				VOICE: TTS_VOICE,
 				SPLIT_ON: TTS_SPLIT_ON,
 				AZURE_SPEECH_REGION: TTS_AZURE_SPEECH_REGION,
-				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT,
+				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT
 			},
 			stt: {
 				OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
@@ -231,7 +231,7 @@
 							<option value="">{$i18n.t('Web API')}</option>
 							<option value="openai">{$i18n.t('OpenAI')}</option>
 							<option value="elevenlabs">{$i18n.t('ElevenLabs')}</option>
-							<option value="azurespeechservice">{$i18n.t('Azure Speech service')}</option>
+							<option value="azure">{$i18n.t('Azure AI Speech')}</option>
 						</select>
 					</div>
 				</div>
@@ -260,7 +260,7 @@
 							/>
 						</div>
 					</div>
-				{:else if TTS_ENGINE === 'azurespeechservice'}
+				{:else if TTS_ENGINE === 'azure'}
 					<div>
 						<div class="mt-1 flex gap-2 mb-1">
 							<input
@@ -276,7 +276,7 @@
 								required
 							/>
 						</div>
-				</div>
+					</div>
 				{/if}
 
 				<hr class=" dark:border-gray-850 my-2" />
@@ -343,88 +343,91 @@
 							</div>
 						</div>
 					</div>
-					{:else if TTS_ENGINE === 'elevenlabs'}
-						<div class=" flex gap-2">
-							<div class="w-full">
-								<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
-								<div class="flex w-full">
-									<div class="flex-1">
-										<input
-											list="voice-list"
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
-											bind:value={TTS_VOICE}
-											placeholder="Select a voice"
-										/>
-	
-										<datalist id="voice-list">
-											{#each voices as voice}
-												<option value={voice.id}>{voice.name}</option>
-											{/each}
-										</datalist>
-									</div>
+				{:else if TTS_ENGINE === 'elevenlabs'}
+					<div class=" flex gap-2">
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="voice-list"
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_VOICE}
+										placeholder="Select a voice"
+									/>
+
+									<datalist id="voice-list">
+										{#each voices as voice}
+											<option value={voice.id}>{voice.name}</option>
+										{/each}
+									</datalist>
 								</div>
 							</div>
-							<div class="w-full">
-								<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Model')}</div>
-								<div class="flex w-full">
-									<div class="flex-1">
-										<input
-											list="tts-model-list"
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
-											bind:value={TTS_MODEL}
-											placeholder="Select a model"
-										/>
-	
-										<datalist id="tts-model-list">
-											{#each models as model}
-												<option value={model.id} />
-											{/each}
-										</datalist>
-									</div>
+						</div>
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Model')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="tts-model-list"
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_MODEL}
+										placeholder="Select a model"
+									/>
+
+									<datalist id="tts-model-list">
+										{#each models as model}
+											<option value={model.id} />
+										{/each}
+									</datalist>
 								</div>
 							</div>
-						</div> 
-					{:else if TTS_ENGINE === 'azurespeechservice'}
-						<div class=" flex gap-2">
-							<div class="w-full">
-								<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
-								<div class="flex w-full">
-									<div class="flex-1">
-										<input
-											list="voice-list"
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
-											bind:value={TTS_VOICE}
-											placeholder="Select a voice"
-										/>
-	
-										<datalist id="voice-list">
-											{#each voices as voice}
-												<option value={voice.id}>{voice.name}</option>
-											{/each}
-										</datalist>
-									</div>
+						</div>
+					</div>
+				{:else if TTS_ENGINE === 'azure'}
+					<div class=" flex gap-2">
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="voice-list"
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_VOICE}
+										placeholder="Select a voice"
+									/>
+
+									<datalist id="voice-list">
+										{#each voices as voice}
+											<option value={voice.id}>{voice.name}</option>
+										{/each}
+									</datalist>
 								</div>
 							</div>
-							<div class="w-full">
-								<div class=" mb-1.5 text-sm font-medium">
-									{$i18n.t('Output format')} 
-									<a href="https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech?tabs=streaming#audio-outputs" target="_blank" >
-										<small>{$i18n.t('Available list')}</small>
-									</a>
-								</div>
-								<div class="flex w-full">
-									<div class="flex-1">
-										<input
-											list="tts-model-list"
-											class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
-											bind:value={TTS_AZURE_SPEECH_OUTPUT_FORMAT}
-											placeholder="Select a output format"
-										/> 
-									</div>
+						</div>
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">
+								{$i18n.t('Output format')}
+								<a
+									href="https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech?tabs=streaming#audio-outputs"
+									target="_blank"
+								>
+									<small>{$i18n.t('Available list')}</small>
+								</a>
+							</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="tts-model-list"
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_AZURE_SPEECH_OUTPUT_FORMAT}
+										placeholder="Select a output format"
+									/>
 								</div>
 							</div>
 						</div>
-					{/if}
+					</div>
+				{/if}
 
 				<hr class="dark:border-gray-850 my-2" />