refac: audio

backend/apps/audio/main.py

@@ -41,10 +41,15 @@ from config import (
     WHISPER_MODEL_DIR,
     WHISPER_MODEL_AUTO_UPDATE,
     DEVICE_TYPE,
-    AUDIO_OPENAI_API_BASE_URL,
-    AUDIO_OPENAI_API_KEY,
-    AUDIO_OPENAI_API_MODEL,
-    AUDIO_OPENAI_API_VOICE,
+    AUDIO_STT_OPENAI_API_BASE_URL,
+    AUDIO_STT_OPENAI_API_KEY,
+    AUDIO_TTS_OPENAI_API_BASE_URL,
+    AUDIO_TTS_OPENAI_API_KEY,
+    AUDIO_STT_ENGINE,
+    AUDIO_STT_MODEL,
+    AUDIO_TTS_ENGINE,
+    AUDIO_TTS_MODEL,
+    AUDIO_TTS_VOICE,
     AppConfig,
 )
 
@@ -61,10 +66,17 @@ app.add_middleware(
 )
 
 app.state.config = AppConfig()
-app.state.config.OPENAI_API_BASE_URL = AUDIO_OPENAI_API_BASE_URL
-app.state.config.OPENAI_API_KEY = AUDIO_OPENAI_API_KEY
-app.state.config.OPENAI_API_MODEL = AUDIO_OPENAI_API_MODEL
-app.state.config.OPENAI_API_VOICE = AUDIO_OPENAI_API_VOICE
+
+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
+app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
+app.state.config.STT_MODEL = AUDIO_STT_MODEL
+
+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
+app.state.config.TTS_MODEL = AUDIO_TTS_MODEL
+app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
 
 # setting device type for whisper model
 whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
@@ -74,41 +86,74 @@ SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
 SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
-class OpenAIConfigUpdateForm(BaseModel):
-    url: str
-    key: str
-    model: str
-    speaker: str
+class TTSConfigForm(BaseModel):
+    OPENAI_API_BASE_URL: str
+    OPENAI_API_KEY: str
+    ENGINE: str
+    MODEL: str
+    VOICE: str
+
+
+class STTConfigForm(BaseModel):
+    OPENAI_API_BASE_URL: str
+    OPENAI_API_KEY: str
+    ENGINE: str
+    MODEL: str
+
+
+class AudioConfigUpdateForm(BaseModel):
+    tts: TTSConfigForm
+    stt: STTConfigForm
 
 
 @app.get("/config")
-async def get_openai_config(user=Depends(get_admin_user)):
+async def get_audio_config(user=Depends(get_admin_user)):
     return {
-        "OPENAI_API_BASE_URL": app.state.config.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.config.OPENAI_API_KEY,
-        "OPENAI_API_MODEL": app.state.config.OPENAI_API_MODEL,
-        "OPENAI_API_VOICE": app.state.config.OPENAI_API_VOICE,
+        "tts": {
+            "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
+            "ENGINE": app.state.config.TTS_ENGINE,
+            "MODEL": app.state.config.TTS_MODEL,
+            "VOICE": app.state.config.TTS_VOICE,
+        },
+        "stt": {
+            "OPENAI_API_BASE_URL": app.state.config.STT_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
+            "ENGINE": app.state.config.STT_ENGINE,
+            "MODEL": app.state.config.STT_MODEL,
+        },
     }
 
 
 @app.post("/config/update")
-async def update_openai_config(
-    form_data: OpenAIConfigUpdateForm, user=Depends(get_admin_user)
+async def update_audio_config(
+    form_data: AudioConfigUpdateForm, user=Depends(get_admin_user)
 ):
-    if form_data.key == "":
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+    app.state.config.TTS_OPENAI_API_BASE_URL = form_data.tts.OPENAI_API_BASE_URL
+    app.state.config.TTS_OPENAI_API_KEY = form_data.tts.OPENAI_API_KEY
+    app.state.config.TTS_ENGINE = form_data.tts.ENGINE
+    app.state.config.TTS_MODEL = form_data.tts.MODEL
+    app.state.config.TTS_VOICE = form_data.tts.VOICE
 
-    app.state.config.OPENAI_API_BASE_URL = form_data.url
-    app.state.config.OPENAI_API_KEY = form_data.key
-    app.state.config.OPENAI_API_MODEL = form_data.model
-    app.state.config.OPENAI_API_VOICE = form_data.speaker
+    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
+    app.state.config.STT_ENGINE = form_data.stt.ENGINE
+    app.state.config.STT_MODEL = form_data.stt.MODEL
 
     return {
-        "status": True,
-        "OPENAI_API_BASE_URL": app.state.config.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.config.OPENAI_API_KEY,
-        "OPENAI_API_MODEL": app.state.config.OPENAI_API_MODEL,
-        "OPENAI_API_VOICE": app.state.config.OPENAI_API_VOICE,
+        "tts": {
+            "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
+            "ENGINE": app.state.config.TTS_ENGINE,
+            "MODEL": app.state.config.TTS_MODEL,
+            "VOICE": app.state.config.TTS_VOICE,
+        },
+        "stt": {
+            "OPENAI_API_BASE_URL": app.state.config.STT_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
+            "ENGINE": app.state.config.STT_ENGINE,
+            "MODEL": app.state.config.STT_MODEL,
+        },
     }
 
 
@@ -125,13 +170,13 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         return FileResponse(file_path)
 
     headers = {}
-    headers["Authorization"] = f"Bearer {app.state.config.OPENAI_API_KEY}"
+    headers["Authorization"] = f"Bearer {app.state.config.TTS_OPENAI_API_KEY}"
     headers["Content-Type"] = "application/json"
 
     r = None
     try:
         r = requests.post(
-            url=f"{app.state.config.OPENAI_API_BASE_URL}/audio/speech",
+            url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
             data=body,
             headers=headers,
             stream=True,

backend/config.py

@@ -933,25 +933,59 @@ IMAGE_GENERATION_MODEL = PersistentConfig(
 # Audio
 ####################################
 
-AUDIO_OPENAI_API_BASE_URL = PersistentConfig(
-    "AUDIO_OPENAI_API_BASE_URL",
-    "audio.openai.api_base_url",
-    os.getenv("AUDIO_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL),
-)
-AUDIO_OPENAI_API_KEY = PersistentConfig(
-    "AUDIO_OPENAI_API_KEY",
-    "audio.openai.api_key",
-    os.getenv("AUDIO_OPENAI_API_KEY", OPENAI_API_KEY),
-)
-AUDIO_OPENAI_API_MODEL = PersistentConfig(
-    "AUDIO_OPENAI_API_MODEL",
-    "audio.openai.api_model",
-    os.getenv("AUDIO_OPENAI_API_MODEL", "tts-1"),
-)
-AUDIO_OPENAI_API_VOICE = PersistentConfig(
-    "AUDIO_OPENAI_API_VOICE",
-    "audio.openai.api_voice",
-    os.getenv("AUDIO_OPENAI_API_VOICE", "alloy"),
+AUDIO_STT_OPENAI_API_BASE_URL = PersistentConfig(
+    "AUDIO_STT_OPENAI_API_BASE_URL",
+    "audio.stt.openai.api_base_url",
+    os.getenv("AUDIO_STT_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL),
+)
+
+AUDIO_STT_OPENAI_API_KEY = PersistentConfig(
+    "AUDIO_STT_OPENAI_API_KEY",
+    "audio.stt.openai.api_key",
+    os.getenv("AUDIO_STT_OPENAI_API_KEY", OPENAI_API_KEY),
+)
+
+AUDIO_STT_ENGINE = PersistentConfig(
+    "AUDIO_STT_ENGINE",
+    "audio.stt.engine",
+    os.getenv("AUDIO_STT_ENGINE", ""),
+)
+
+AUDIO_STT_MODEL = PersistentConfig(
+    "AUDIO_STT_MODEL",
+    "audio.stt.model",
+    os.getenv("AUDIO_STT_MODEL", "whisper-1"),
+)
+
+AUDIO_TTS_OPENAI_API_BASE_URL = PersistentConfig(
+    "AUDIO_TTS_OPENAI_API_BASE_URL",
+    "audio.tts.openai.api_base_url",
+    os.getenv("AUDIO_TTS_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL),
+)
+AUDIO_TTS_OPENAI_API_KEY = PersistentConfig(
+    "AUDIO_TTS_OPENAI_API_KEY",
+    "audio.tts.openai.api_key",
+    os.getenv("AUDIO_TTS_OPENAI_API_KEY", OPENAI_API_KEY),
+)
+
+
+AUDIO_TTS_ENGINE = PersistentConfig(
+    "AUDIO_TTS_ENGINE",
+    "audio.tts.engine",
+    os.getenv("AUDIO_TTS_ENGINE", ""),
+)
+
+
+AUDIO_TTS_MODEL = PersistentConfig(
+    "AUDIO_TTS_MODEL",
+    "audio.tts.model",
+    os.getenv("AUDIO_TTS_MODEL", "tts-1"),
+)
+
+AUDIO_TTS_VOICE = PersistentConfig(
+    "AUDIO_TTS_VOICE",
+    "audio.tts.voice",
+    os.getenv("AUDIO_TTS_VOICE", "alloy"),
 )
 
 

backend/main.py

@@ -900,6 +900,15 @@ async def get_app_config():
             "enable_community_sharing": webui_app.state.config.ENABLE_COMMUNITY_SHARING,
             "enable_admin_export": ENABLE_ADMIN_EXPORT,
         },
+        "audio": {
+            "tts": {
+                "engine": audio_app.state.config.TTS_ENGINE,
+                "voice": audio_app.state.config.TTS_VOICE,
+            },
+            "stt": {
+                "engine": audio_app.state.config.STT_ENGINE,
+            },
+        },
     }
 
 

src/lib/components/admin/Settings.svelte

@@ -0,0 +1,227 @@
+<script>
+	import { getContext } from 'svelte';
+	import Modal from '../common/Modal.svelte';
+	import Database from './Settings/Database.svelte';
+
+	import General from './Settings/General.svelte';
+	import Users from './Settings/Users.svelte';
+
+	import Banners from '$lib/components/admin/Settings/Banners.svelte';
+	import { toast } from 'svelte-sonner';
+	import Pipelines from './Settings/Pipelines.svelte';
+	import Audio from './Settings/Audio.svelte';
+
+	const i18n = getContext('i18n');
+
+	let selectedTab = 'general';
+</script>
+
+<div class="flex flex-col md:flex-row w-full h-full py-3 md:space-x-4">
+	<div
+		class="tabs flex flex-row overflow-x-auto space-x-1 md:space-x-0 md:space-y-1 md:flex-col md:flex-none md:w-40 dark:text-gray-200 text-xs text-left mb-3 md:mb-0 scrollbar-hidden"
+	>
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'general'
+				? 'bg-gray-200 dark:bg-gray-700'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+			on:click={() => {
+				selectedTab = 'general';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						fill-rule="evenodd"
+						d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
+						clip-rule="evenodd"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('General')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'users'
+				? 'bg-gray-200 dark:bg-gray-700'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+			on:click={() => {
+				selectedTab = 'users';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						d="M8 8a2.5 2.5 0 1 0 0-5 2.5 2.5 0 0 0 0 5ZM3.156 11.763c.16-.629.44-1.21.813-1.72a2.5 2.5 0 0 0-2.725 1.377c-.136.287.102.58.418.58h1.449c.01-.077.025-.156.045-.237ZM12.847 11.763c.02.08.036.16.046.237h1.446c.316 0 .554-.293.417-.579a2.5 2.5 0 0 0-2.722-1.378c.374.51.653 1.09.813 1.72ZM14 7.5a1.5 1.5 0 1 1-3 0 1.5 1.5 0 0 1 3 0ZM3.5 9a1.5 1.5 0 1 0 0-3 1.5 1.5 0 0 0 0 3ZM5 13c-.552 0-1.013-.455-.876-.99a4.002 4.002 0 0 1 7.753 0c.136.535-.324.99-.877.99H5Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Users')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'audio'
+				? 'bg-gray-200 dark:bg-gray-700'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+			on:click={() => {
+				selectedTab = 'audio';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						d="M7.557 2.066A.75.75 0 0 1 8 2.75v10.5a.75.75 0 0 1-1.248.56L3.59 11H2a1 1 0 0 1-1-1V6a1 1 0 0 1 1-1h1.59l3.162-2.81a.75.75 0 0 1 .805-.124ZM12.95 3.05a.75.75 0 1 0-1.06 1.06 5.5 5.5 0 0 1 0 7.78.75.75 0 1 0 1.06 1.06 7 7 0 0 0 0-9.9Z"
+					/>
+					<path
+						d="M10.828 5.172a.75.75 0 1 0-1.06 1.06 2.5 2.5 0 0 1 0 3.536.75.75 0 1 0 1.06 1.06 4 4 0 0 0 0-5.656Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Audio')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'banners'
+				? 'bg-gray-200 dark:bg-gray-700'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+			on:click={() => {
+				selectedTab = 'banners';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 24 24"
+					fill="currentColor"
+					class="size-4"
+				>
+					<path
+						d="M5.85 3.5a.75.75 0 0 0-1.117-1 9.719 9.719 0 0 0-2.348 4.876.75.75 0 0 0 1.479.248A8.219 8.219 0 0 1 5.85 3.5ZM19.267 2.5a.75.75 0 1 0-1.118 1 8.22 8.22 0 0 1 1.987 4.124.75.75 0 0 0 1.48-.248A9.72 9.72 0 0 0 19.266 2.5Z"
+					/>
+					<path
+						fill-rule="evenodd"
+						d="M12 2.25A6.75 6.75 0 0 0 5.25 9v.75a8.217 8.217 0 0 1-2.119 5.52.75.75 0 0 0 .298 1.206c1.544.57 3.16.99 4.831 1.243a3.75 3.75 0 1 0 7.48 0 24.583 24.583 0 0 0 4.83-1.244.75.75 0 0 0 .298-1.205 8.217 8.217 0 0 1-2.118-5.52V9A6.75 6.75 0 0 0 12 2.25ZM9.75 18c0-.034 0-.067.002-.1a25.05 25.05 0 0 0 4.496 0l.002.1a2.25 2.25 0 1 1-4.5 0Z"
+						clip-rule="evenodd"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Banners')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'pipelines'
+				? 'bg-gray-200 dark:bg-gray-700'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+			on:click={() => {
+				selectedTab = 'pipelines';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 24 24"
+					fill="currentColor"
+					class="size-4"
+				>
+					<path
+						d="M11.644 1.59a.75.75 0 0 1 .712 0l9.75 5.25a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.712 0l-9.75-5.25a.75.75 0 0 1 0-1.32l9.75-5.25Z"
+					/>
+					<path
+						d="m3.265 10.602 7.668 4.129a2.25 2.25 0 0 0 2.134 0l7.668-4.13 1.37.739a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.71 0l-9.75-5.25a.75.75 0 0 1 0-1.32l1.37-.738Z"
+					/>
+					<path
+						d="m10.933 19.231-7.668-4.13-1.37.739a.75.75 0 0 0 0 1.32l9.75 5.25c.221.12.489.12.71 0l9.75-5.25a.75.75 0 0 0 0-1.32l-1.37-.738-7.668 4.13a2.25 2.25 0 0 1-2.134-.001Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Pipelines')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'db'
+				? 'bg-gray-200 dark:bg-gray-700'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+			on:click={() => {
+				selectedTab = 'db';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path d="M8 7c3.314 0 6-1.343 6-3s-2.686-3-6-3-6 1.343-6 3 2.686 3 6 3Z" />
+					<path
+						d="M8 8.5c1.84 0 3.579-.37 4.914-1.037A6.33 6.33 0 0 0 14 6.78V8c0 1.657-2.686 3-6 3S2 9.657 2 8V6.78c.346.273.72.5 1.087.683C4.42 8.131 6.16 8.5 8 8.5Z"
+					/>
+					<path
+						d="M8 12.5c1.84 0 3.579-.37 4.914-1.037.366-.183.74-.41 1.086-.684V12c0 1.657-2.686 3-6 3s-6-1.343-6-3v-1.22c.346.273.72.5 1.087.683C4.42 12.131 6.16 12.5 8 12.5Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Database')}</div>
+		</button>
+	</div>
+
+	<div class="flex-1">
+		{#if selectedTab === 'general'}
+			<General
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'users'}
+			<Users
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'audio'}
+			<Audio
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'db'}
+			<Database
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'banners'}
+			<Banners
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'pipelines'}
+			<Pipelines
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{/if}
+	</div>
+</div>

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

@@ -0,0 +1,310 @@
+<script lang="ts">
+	import { getAudioConfig, updateAudioConfig } from '$lib/apis/audio';
+	import { user, settings, config } from '$lib/stores';
+	import { createEventDispatcher, onMount, getContext } from 'svelte';
+	import { toast } from 'svelte-sonner';
+	import Switch from '$lib/components/common/Switch.svelte';
+	import { getBackendConfig } from '$lib/apis';
+	const dispatch = createEventDispatcher();
+
+	const i18n = getContext('i18n');
+
+	export let saveHandler: Function;
+
+	// Audio
+
+	let TTS_OPENAI_API_BASE_URL = '';
+	let TTS_OPENAI_API_KEY = '';
+	let TTS_ENGINE = '';
+	let TTS_MODEL = '';
+	let TTS_VOICE = '';
+
+	let STT_OPENAI_API_BASE_URL = '';
+	let STT_OPENAI_API_KEY = '';
+	let STT_ENGINE = '';
+	let STT_MODEL = '';
+
+	let voices = [];
+	let models = [];
+	let nonLocalVoices = false;
+
+	const getOpenAIVoices = () => {
+		voices = [
+			{ name: 'alloy' },
+			{ name: 'echo' },
+			{ name: 'fable' },
+			{ name: 'onyx' },
+			{ name: 'nova' },
+			{ name: 'shimmer' }
+		];
+	};
+
+	const getOpenAIModels = () => {
+		models = [{ name: 'tts-1' }, { name: 'tts-1-hd' }];
+	};
+
+	const getWebAPIVoices = () => {
+		const getVoicesLoop = setInterval(async () => {
+			voices = await speechSynthesis.getVoices();
+
+			// do your loop
+			if (voices.length > 0) {
+				clearInterval(getVoicesLoop);
+			}
+		}, 100);
+	};
+
+	const updateConfigHandler = async () => {
+		const res = await updateAudioConfig(localStorage.token, {
+			tts: {
+				OPENAI_API_BASE_URL: TTS_OPENAI_API_BASE_URL,
+				OPENAI_API_KEY: TTS_OPENAI_API_KEY,
+				ENGINE: TTS_ENGINE,
+				MODEL: TTS_MODEL,
+				VOICE: TTS_VOICE
+			},
+			stt: {
+				OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
+				OPENAI_API_KEY: STT_OPENAI_API_KEY,
+				ENGINE: STT_ENGINE,
+				MODEL: STT_MODEL
+			}
+		});
+
+		if (res) {
+			toast.success('Audio settings updated successfully');
+
+			config.set(await getBackendConfig());
+		}
+	};
+
+	onMount(async () => {
+		const res = await getAudioConfig(localStorage.token);
+
+		if (res) {
+			console.log(res);
+			TTS_OPENAI_API_BASE_URL = res.tts.OPENAI_API_BASE_URL;
+			TTS_OPENAI_API_KEY = res.tts.OPENAI_API_KEY;
+
+			TTS_ENGINE = res.tts.ENGINE;
+			TTS_MODEL = res.tts.MODEL;
+			TTS_VOICE = res.tts.VOICE;
+
+			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;
+		}
+
+		if (TTS_ENGINE === 'openai') {
+			getOpenAIVoices();
+			getOpenAIModels();
+		} else {
+			getWebAPIVoices();
+		}
+	});
+</script>
+
+<form
+	class="flex flex-col h-full justify-between space-y-3 text-sm"
+	on:submit|preventDefault={async () => {
+		await updateConfigHandler();
+		dispatch('save');
+	}}
+>
+	<div class="flex flex-col gap-3">
+		<div>
+			<div class=" mb-1 text-sm font-medium">{$i18n.t('STT Settings')}</div>
+
+			<div class=" py-0.5 flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
+				<div class="flex items-center relative">
+					<select
+						class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+						bind:value={STT_ENGINE}
+						placeholder="Select an engine"
+					>
+						<option value="">{$i18n.t('Local Whisper')}</option>
+						<option value="openai">OpenAI</option>
+						<option value="web">{$i18n.t('Web API')}</option>
+					</select>
+				</div>
+			</div>
+
+			{#if STT_ENGINE === 'openai'}
+				<div>
+					<div class="mt-1 flex gap-2 mb-1">
+						<input
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							placeholder={$i18n.t('API Base URL')}
+							bind:value={STT_OPENAI_API_BASE_URL}
+							required
+						/>
+
+						<input
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							placeholder={$i18n.t('API Key')}
+							bind:value={STT_OPENAI_API_KEY}
+							required
+						/>
+					</div>
+				</div>
+
+				<hr class=" dark:border-gray-850 my-2" />
+
+				<div>
+					<div class=" mb-1.5 text-sm font-medium">{$i18n.t('STT Model')}</div>
+					<div class="flex w-full">
+						<div class="flex-1">
+							<input
+								list="model-list"
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								bind:value={STT_MODEL}
+								placeholder="Select a model"
+							/>
+
+							<datalist id="model-list">
+								<option value="whisper-1" />
+							</datalist>
+						</div>
+					</div>
+				</div>
+			{/if}
+		</div>
+
+		<hr class=" dark:border-gray-800" />
+
+		<div>
+			<div class=" mb-1 text-sm font-medium">{$i18n.t('TTS Settings')}</div>
+
+			<div class=" py-0.5 flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('Text-to-Speech Engine')}</div>
+				<div class="flex items-center relative">
+					<select
+						class=" dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+						bind:value={TTS_ENGINE}
+						placeholder="Select a mode"
+						on:change={(e) => {
+							if (e.target.value === 'openai') {
+								getOpenAIVoices();
+								TTS_VOICE = 'alloy';
+								TTS_MODEL = 'tts-1';
+							} else {
+								getWebAPIVoices();
+								TTS_VOICE = '';
+							}
+						}}
+					>
+						<option value="">{$i18n.t('Web API')}</option>
+						<option value="openai">{$i18n.t('Open AI')}</option>
+					</select>
+				</div>
+			</div>
+
+			{#if TTS_ENGINE === 'openai'}
+				<div>
+					<div class="mt-1 flex gap-2 mb-1">
+						<input
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							placeholder={$i18n.t('API Base URL')}
+							bind:value={TTS_OPENAI_API_BASE_URL}
+							required
+						/>
+
+						<input
+							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							placeholder={$i18n.t('API Key')}
+							bind:value={TTS_OPENAI_API_KEY}
+							required
+						/>
+					</div>
+				</div>
+			{/if}
+
+			<hr class=" dark:border-gray-850 my-2" />
+
+			{#if TTS_ENGINE === ''}
+				<div>
+					<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+					<div class="flex w-full">
+						<div class="flex-1">
+							<select
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								bind:value={TTS_VOICE}
+							>
+								<option value="" selected={TTS_VOICE !== ''}>{$i18n.t('Default')}</option>
+								{#each voices.filter((v) => nonLocalVoices || v.localService === true) as voice}
+									<option
+										value={voice.voiceURI}
+										class="bg-gray-100 dark:bg-gray-700"
+										selected={TTS_VOICE === voice.voiceURI}>{voice.name}</option
+									>
+								{/each}
+							</select>
+						</div>
+					</div>
+					<div class="flex items-center justify-between my-1.5">
+						<div class="text-xs">
+							{$i18n.t('Allow non-local voices')}
+						</div>
+
+						<div class="mt-1">
+							<Switch bind:state={nonLocalVoices} />
+						</div>
+					</div>
+				</div>
+			{:else if TTS_ENGINE === 'openai'}
+				<div class=" flex gap-2">
+					<div class="w-full">
+						<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+						<div class="flex w-full">
+							<div class="flex-1">
+								<input
+									list="voice-list"
+									class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+									bind:value={TTS_VOICE}
+									placeholder="Select a voice"
+								/>
+
+								<datalist id="voice-list">
+									{#each voices as voice}
+										<option value={voice.name} />
+									{/each}
+								</datalist>
+							</div>
+						</div>
+					</div>
+					<div class="w-full">
+						<div class=" mb-2.5 text-sm font-medium">{$i18n.t('TTS Model')}</div>
+						<div class="flex w-full">
+							<div class="flex-1">
+								<input
+									list="model-list"
+									class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+									bind:value={TTS_MODEL}
+									placeholder="Select a model"
+								/>
+
+								<datalist id="model-list">
+									{#each models as model}
+										<option value={model.name} />
+									{/each}
+								</datalist>
+							</div>
+						</div>
+					</div>
+				</div>
+			{/if}
+		</div>
+	</div>
+
+	<div class="flex justify-end text-sm font-medium">
+		<button
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
+			type="submit"
+		>
+			{$i18n.t('Save')}
+		</button>
+	</div>
+</form>

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

@@ -33,7 +33,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80 h-full">
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll h-full">
 		<div class=" space-y-3 pr-1.5">
 			<div class="flex w-full justify-between mb-2">
 				<div class=" self-center text-sm font-semibold">

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

@@ -30,7 +30,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll h-full">
 		<div>
 			<div class=" mb-2 text-sm font-medium">{$i18n.t('Database')}</div>
 

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

@@ -56,7 +56,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-[22rem]">
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll h-full">
 		{#if adminConfig !== null}
 			<div>
 				<div class=" mb-3 text-sm font-medium">{$i18n.t('General Settings')}</div>

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

@@ -200,7 +200,7 @@
 		updateHandler();
 	}}
 >
-	<div class="  pr-1.5 overflow-y-scroll max-h-80 h-full">
+	<div class="  pr-1.5 overflow-y-scroll h-full">
 		{#if PIPELINES_LIST !== null}
 			<div class="flex w-full justify-between mb-2">
 				<div class=" self-center text-sm font-semibold">

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

@@ -48,7 +48,7 @@
 		await config.set(await getBackendConfig());
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-full">
 		<div>
 			<div class=" mb-2 text-sm font-medium">{$i18n.t('User Permissions')}</div>
 

src/lib/components/admin/SettingsModal.svelte

@@ -39,181 +39,5 @@
 				</svg>
 			</button>
 		</div>
-
-		<div class="flex flex-col md:flex-row w-full p-4 md:space-x-4">
-			<div
-				class="tabs flex flex-row overflow-x-auto space-x-1 md:space-x-0 md:space-y-1 md:flex-col flex-1 md:flex-none md:w-40 dark:text-gray-200 text-xs text-left mb-3 md:mb-0"
-			>
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'general'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'general';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path
-								fill-rule="evenodd"
-								d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
-								clip-rule="evenodd"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('General')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'users'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'users';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path
-								d="M8 8a2.5 2.5 0 1 0 0-5 2.5 2.5 0 0 0 0 5ZM3.156 11.763c.16-.629.44-1.21.813-1.72a2.5 2.5 0 0 0-2.725 1.377c-.136.287.102.58.418.58h1.449c.01-.077.025-.156.045-.237ZM12.847 11.763c.02.08.036.16.046.237h1.446c.316 0 .554-.293.417-.579a2.5 2.5 0 0 0-2.722-1.378c.374.51.653 1.09.813 1.72ZM14 7.5a1.5 1.5 0 1 1-3 0 1.5 1.5 0 0 1 3 0ZM3.5 9a1.5 1.5 0 1 0 0-3 1.5 1.5 0 0 0 0 3ZM5 13c-.552 0-1.013-.455-.876-.99a4.002 4.002 0 0 1 7.753 0c.136.535-.324.99-.877.99H5Z"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Users')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'db'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'db';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path d="M8 7c3.314 0 6-1.343 6-3s-2.686-3-6-3-6 1.343-6 3 2.686 3 6 3Z" />
-							<path
-								d="M8 8.5c1.84 0 3.579-.37 4.914-1.037A6.33 6.33 0 0 0 14 6.78V8c0 1.657-2.686 3-6 3S2 9.657 2 8V6.78c.346.273.72.5 1.087.683C4.42 8.131 6.16 8.5 8 8.5Z"
-							/>
-							<path
-								d="M8 12.5c1.84 0 3.579-.37 4.914-1.037.366-.183.74-.41 1.086-.684V12c0 1.657-2.686 3-6 3s-6-1.343-6-3v-1.22c.346.273.72.5 1.087.683C4.42 12.131 6.16 12.5 8 12.5Z"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Database')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'banners'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'banners';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 24 24"
-							fill="currentColor"
-							class="size-4"
-						>
-							<path
-								d="M5.85 3.5a.75.75 0 0 0-1.117-1 9.719 9.719 0 0 0-2.348 4.876.75.75 0 0 0 1.479.248A8.219 8.219 0 0 1 5.85 3.5ZM19.267 2.5a.75.75 0 1 0-1.118 1 8.22 8.22 0 0 1 1.987 4.124.75.75 0 0 0 1.48-.248A9.72 9.72 0 0 0 19.266 2.5Z"
-							/>
-							<path
-								fill-rule="evenodd"
-								d="M12 2.25A6.75 6.75 0 0 0 5.25 9v.75a8.217 8.217 0 0 1-2.119 5.52.75.75 0 0 0 .298 1.206c1.544.57 3.16.99 4.831 1.243a3.75 3.75 0 1 0 7.48 0 24.583 24.583 0 0 0 4.83-1.244.75.75 0 0 0 .298-1.205 8.217 8.217 0 0 1-2.118-5.52V9A6.75 6.75 0 0 0 12 2.25ZM9.75 18c0-.034 0-.067.002-.1a25.05 25.05 0 0 0 4.496 0l.002.1a2.25 2.25 0 1 1-4.5 0Z"
-								clip-rule="evenodd"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Banners')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'pipelines'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'pipelines';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 24 24"
-							fill="currentColor"
-							class="size-4"
-						>
-							<path
-								d="M11.644 1.59a.75.75 0 0 1 .712 0l9.75 5.25a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.712 0l-9.75-5.25a.75.75 0 0 1 0-1.32l9.75-5.25Z"
-							/>
-							<path
-								d="m3.265 10.602 7.668 4.129a2.25 2.25 0 0 0 2.134 0l7.668-4.13 1.37.739a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.71 0l-9.75-5.25a.75.75 0 0 1 0-1.32l1.37-.738Z"
-							/>
-							<path
-								d="m10.933 19.231-7.668-4.13-1.37.739a.75.75 0 0 0 0 1.32l9.75 5.25c.221.12.489.12.71 0l9.75-5.25a.75.75 0 0 0 0-1.32l-1.37-.738-7.668 4.13a2.25 2.25 0 0 1-2.134-.001Z"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Pipelines')}</div>
-				</button>
-			</div>
-			<div class="flex-1 md:min-h-[380px]">
-				{#if selectedTab === 'general'}
-					<General
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'users'}
-					<Users
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'db'}
-					<Database
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'banners'}
-					<Banners
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'pipelines'}
-					<Pipelines
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{/if}
-			</div>
-		</div>
 	</div>
 </Modal>

src/lib/components/chat/MessageInput/CallOverlay.svelte

@@ -1,5 +1,5 @@
 <script lang="ts">
-	import { settings, showCallOverlay } from '$lib/stores';
+	import { config, settings, showCallOverlay } from '$lib/stores';
 	import { onMount, tick, getContext } from 'svelte';
 
 	import { blobToFile, calculateSHA256, extractSentences, findWordIndices } from '$lib/utils';
@@ -159,9 +159,9 @@
 	const getOpenAISpeech = async (text) => {
 		const res = await synthesizeOpenAISpeech(
 			localStorage.token,
-			$settings?.audio?.speaker ?? 'alloy',
+			$settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice,
 			text,
-			$settings?.audio?.model ?? 'tts-1'
+			$settings?.audio?.tts?.model ?? $config?.audio?.tts?.model
 		).catch((error) => {
 			toast.error(error);
 			assistantSpeaking = false;
@@ -207,10 +207,29 @@
 	const assistantSpeakingHandler = async (content) => {
 		assistantSpeaking = true;
 
-		if (($settings?.audio?.TTSEngine ?? '') == '') {
-			currentUtterance = new SpeechSynthesisUtterance(content);
-			speechSynthesis.speak(currentUtterance);
-		} else if ($settings?.audio?.TTSEngine === 'openai') {
+		if (($config.audio.tts.engine ?? '') == '') {
+			let voices = [];
+			const getVoicesLoop = setInterval(async () => {
+				voices = await speechSynthesis.getVoices();
+				if (voices.length > 0) {
+					clearInterval(getVoicesLoop);
+
+					const voice =
+						voices
+							?.filter(
+								(v) => v.voiceURI === ($settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice)
+							)
+							?.at(0) ?? undefined;
+
+					console.log($settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice);
+					console.log(voices);
+
+					currentUtterance = new SpeechSynthesisUtterance(content);
+					currentUtterance.voice = voice;
+					speechSynthesis.speak(currentUtterance);
+				}
+			}, 100);
+		} else if ($config.audio.tts.engine === 'openai') {
 			console.log('openai');
 
 			const sentences = extractSentences(content).reduce((mergedTexts, currentText) => {
@@ -236,9 +255,9 @@
 			for (const [idx, sentence] of sentences.entries()) {
 				const res = await synthesizeOpenAISpeech(
 					localStorage.token,
-					$settings?.audio?.speaker,
+					$settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice,
 					sentence,
-					$settings?.audio?.model
+					$settings?.audio?.tts?.model ?? $config?.audio?.tts?.model
 				).catch((error) => {
 					toast.error(error);
 

src/lib/components/chat/MessageInput/VoiceRecording.svelte

@@ -169,7 +169,7 @@
 		mediaRecorder.ondataavailable = (event) => audioChunks.push(event.data);
 		mediaRecorder.onstop = async () => {
 			console.log('Recording stopped');
-			if (($settings?.audio?.STTEngine ?? '') === 'web') {
+			if (($settings?.audio?.stt?.engine ?? '') === 'web') {
 				audioChunks = [];
 			} else {
 				if (confirmed) {
@@ -186,7 +186,7 @@
 		};
 		mediaRecorder.start();
 
-		if (($settings?.audio?.STTEngine ?? '') === 'web') {
+		if (($settings?.audio?.stt?.engine ?? '') === 'web') {
 			if ('SpeechRecognition' in window || 'webkitSpeechRecognition' in window) {
 				// Create a SpeechRecognition object
 				speechRecognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -213,7 +213,7 @@
 		} else {
 			speaking = true;
 
-			if ($settings?.audio?.TTSEngine === 'openai') {
+			if ($config.audio.tts.engine === 'openai') {
 				loadingSpeech = true;
 
 				const sentences = extractSentences(message.content).reduce((mergedTexts, currentText) => {
@@ -244,9 +244,9 @@
 				for (const [idx, sentence] of sentences.entries()) {
 					const res = await synthesizeOpenAISpeech(
 						localStorage.token,
-						$settings?.audio?.speaker,
+						$settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice,
 						sentence,
-						$settings?.audio?.model
+						$settings?.audio?.tts?.model ?? $config?.audio?.tts?.model
 					).catch((error) => {
 						toast.error(error);
 
@@ -273,7 +273,11 @@
 						clearInterval(getVoicesLoop);
 
 						const voice =
-							voices?.filter((v) => v.name === $settings?.audio?.speaker)?.at(0) ?? undefined;
+							voices
+								?.filter(
+									(v) => v.voiceURI === ($settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice)
+								)
+								?.at(0) ?? undefined;
 
 						const speak = new SpeechSynthesisUtterance(message.content);
 

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

@@ -1,6 +1,5 @@
 <script lang="ts">
-	import { getAudioConfig, updateAudioConfig } from '$lib/apis/audio';
-	import { user, settings } from '$lib/stores';
+	import { user, settings, config } from '$lib/stores';
 	import { createEventDispatcher, onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
 	import Switch from '$lib/components/common/Switch.svelte';
@@ -11,26 +10,15 @@
 	export let saveSettings: Function;
 
 	// Audio
-
-	let OpenAIUrl = '';
-	let OpenAIKey = '';
-	let OpenAISpeaker = '';
-
-	let STTEngines = ['', 'openai'];
-	let STTEngine = '';
-
 	let conversationMode = false;
 	let speechAutoSend = false;
 	let responseAutoPlayback = false;
 	let nonLocalVoices = false;
 
-	let TTSEngines = ['', 'openai'];
-	let TTSEngine = '';
+	let STTEngine = '';
 
 	let voices = [];
-	let speaker = '';
-	let models = [];
-	let model = '';
+	let voice = '';
 
 	const getOpenAIVoices = () => {
 		voices = [
@@ -43,10 +31,6 @@
 		];
 	};
 
-	const getOpenAIVoicesModel = () => {
-		models = [{ name: 'tts-1' }, { name: 'tts-1-hd' }];
-	};
-
 	const getWebAPIVoices = () => {
 		const getVoicesLoop = setInterval(async () => {
 			voices = await speechSynthesis.getVoices();
@@ -58,21 +42,6 @@
 		}, 100);
 	};
 
-	const toggleConversationMode = async () => {
-		conversationMode = !conversationMode;
-
-		if (conversationMode) {
-			responseAutoPlayback = true;
-			speechAutoSend = true;
-		}
-
-		saveSettings({
-			conversationMode: conversationMode,
-			responseAutoPlayback: responseAutoPlayback,
-			speechAutoSend: speechAutoSend
-		});
-	};
-
 	const toggleResponseAutoPlayback = async () => {
 		responseAutoPlayback = !responseAutoPlayback;
 		saveSettings({ responseAutoPlayback: responseAutoPlayback });
@@ -83,76 +52,35 @@
 		saveSettings({ speechAutoSend: speechAutoSend });
 	};
 
-	const updateConfigHandler = async () => {
-		if (TTSEngine === 'openai') {
-			const res = await updateAudioConfig(localStorage.token, {
-				url: OpenAIUrl,
-				key: OpenAIKey,
-				model: model,
-				speaker: OpenAISpeaker
-			});
-
-			if (res) {
-				OpenAIUrl = res.OPENAI_API_BASE_URL;
-				OpenAIKey = res.OPENAI_API_KEY;
-				model = res.OPENAI_API_MODEL;
-				OpenAISpeaker = res.OPENAI_API_VOICE;
-			}
-		}
-	};
-
 	onMount(async () => {
 		conversationMode = $settings.conversationMode ?? false;
 		speechAutoSend = $settings.speechAutoSend ?? false;
 		responseAutoPlayback = $settings.responseAutoPlayback ?? false;
 
-		STTEngine = $settings?.audio?.STTEngine ?? '';
-		TTSEngine = $settings?.audio?.TTSEngine ?? '';
-		nonLocalVoices = $settings.audio?.nonLocalVoices ?? false;
-		speaker = $settings?.audio?.speaker ?? '';
-		model = $settings?.audio?.model ?? '';
+		STTEngine = $settings?.audio?.stt?.engine ?? '';
+		voice = $settings?.audio?.tts?.voice ?? $config.audio.tts.voice ?? '';
+		nonLocalVoices = $settings.audio?.tts?.nonLocalVoices ?? false;
 
-		if (TTSEngine === 'openai') {
+		if ($config.audio.tts.engine === 'openai') {
 			getOpenAIVoices();
-			getOpenAIVoicesModel();
 		} else {
 			getWebAPIVoices();
 		}
-
-		if ($user.role === 'admin') {
-			const res = await getAudioConfig(localStorage.token);
-
-			if (res) {
-				OpenAIUrl = res.OPENAI_API_BASE_URL;
-				OpenAIKey = res.OPENAI_API_KEY;
-				model = res.OPENAI_API_MODEL;
-				OpenAISpeaker = res.OPENAI_API_VOICE;
-				if (TTSEngine === 'openai') {
-					speaker = OpenAISpeaker;
-				}
-			}
-		}
 	});
 </script>
 
 <form
 	class="flex flex-col h-full justify-between space-y-3 text-sm"
 	on:submit|preventDefault={async () => {
-		if ($user.role === 'admin') {
-			await updateConfigHandler();
-		}
 		saveSettings({
 			audio: {
-				STTEngine: STTEngine !== '' ? STTEngine : undefined,
-				TTSEngine: TTSEngine !== '' ? TTSEngine : undefined,
-				speaker:
-					(TTSEngine === 'openai' ? OpenAISpeaker : speaker) !== ''
-						? TTSEngine === 'openai'
-							? OpenAISpeaker
-							: speaker
-						: undefined,
-				model: model !== '' ? model : undefined,
-				nonLocalVoices: nonLocalVoices
+				stt: {
+					engine: STTEngine !== '' ? STTEngine : undefined
+				},
+				tts: {
+					voice: $config.audio.tts.engine === 'openai' ? voice : voice !== '' ? voice : undefined,
+					nonLocalVoices: $config.audio.tts.engine === '' ? nonLocalVoices : undefined
+				}
 			}
 		});
 		dispatch('save');
@@ -162,31 +90,21 @@
 		<div>
 			<div class=" mb-1 text-sm font-medium">{$i18n.t('STT Settings')}</div>
 
-			<div class=" py-0.5 flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
-				<div class="flex items-center relative">
-					<select
-						class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
-						bind:value={STTEngine}
-						placeholder="Select an engine"
-						on:change={(e) => {
-							if (e.target.value !== '') {
-								navigator.mediaDevices.getUserMedia({ audio: true }).catch(function (err) {
-									toast.error(
-										$i18n.t(`Permission denied when accessing microphone: {{error}}`, {
-											error: err
-										})
-									);
-									STTEngine = '';
-								});
-							}
-						}}
-					>
-						<option value="">{$i18n.t('Default (Whisper)')}</option>
-						<option value="web">{$i18n.t('Web API')}</option>
-					</select>
+			{#if $config.audio.stt.engine !== 'web'}
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
+					<div class="flex items-center relative">
+						<select
+							class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+							bind:value={STTEngine}
+							placeholder="Select an engine"
+						>
+							<option value="">{$i18n.t('Default')}</option>
+							<option value="web">{$i18n.t('Web API')}</option>
+						</select>
+					</div>
 				</div>
-			</div>
+			{/if}
 
 			<div class=" py-0.5 flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">
@@ -212,50 +130,6 @@
 		<div>
 			<div class=" mb-1 text-sm font-medium">{$i18n.t('TTS Settings')}</div>
 
-			<div class=" py-0.5 flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('Text-to-Speech Engine')}</div>
-				<div class="flex items-center relative">
-					<select
-						class=" dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
-						bind:value={TTSEngine}
-						placeholder="Select a mode"
-						on:change={(e) => {
-							if (e.target.value === 'openai') {
-								getOpenAIVoices();
-								OpenAISpeaker = 'alloy';
-								model = 'tts-1';
-							} else {
-								getWebAPIVoices();
-								speaker = '';
-							}
-						}}
-					>
-						<option value="">{$i18n.t('Default (Web API)')}</option>
-						<option value="openai">{$i18n.t('Open AI')}</option>
-					</select>
-				</div>
-			</div>
-
-			{#if $user.role === 'admin'}
-				{#if TTSEngine === 'openai'}
-					<div class="mt-1 flex gap-2 mb-1">
-						<input
-							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							placeholder={$i18n.t('API Base URL')}
-							bind:value={OpenAIUrl}
-							required
-						/>
-
-						<input
-							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							placeholder={$i18n.t('API Key')}
-							bind:value={OpenAIKey}
-							required
-						/>
-					</div>
-				{/if}
-			{/if}
-
 			<div class=" py-0.5 flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">{$i18n.t('Auto-playback response')}</div>
 
@@ -277,21 +151,21 @@
 
 		<hr class=" dark:border-gray-700" />
 
-		{#if TTSEngine === ''}
+		{#if $config.audio.tts.engine === ''}
 			<div>
 				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Voice')}</div>
 				<div class="flex w-full">
 					<div class="flex-1">
 						<select
 							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							bind:value={speaker}
+							bind:value={voice}
 						>
-							<option value="" selected={speaker !== ''}>{$i18n.t('Default')}</option>
-							{#each voices.filter((v) => nonLocalVoices || v.localService === true) as voice}
+							<option value="" selected={voice !== ''}>{$i18n.t('Default')}</option>
+							{#each voices.filter((v) => nonLocalVoices || v.localService === true) as _voice}
 								<option
-									value={voice.name}
+									value={_voice.name}
 									class="bg-gray-100 dark:bg-gray-700"
-									selected={speaker === voice.name}>{voice.name}</option
+									selected={voice === _voice.name}>{_voice.name}</option
 								>
 							{/each}
 						</select>
@@ -307,7 +181,7 @@
 					</div>
 				</div>
 			</div>
-		{:else if TTSEngine === 'openai'}
+		{:else if $config.audio.tts.engine === 'openai'}
 			<div>
 				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Voice')}</div>
 				<div class="flex w-full">
@@ -315,7 +189,7 @@
 						<input
 							list="voice-list"
 							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							bind:value={OpenAISpeaker}
+							bind:value={voice}
 							placeholder="Select a voice"
 						/>
 
@@ -327,25 +201,6 @@
 					</div>
 				</div>
 			</div>
-			<div>
-				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Model')}</div>
-				<div class="flex w-full">
-					<div class="flex-1">
-						<input
-							list="model-list"
-							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							bind:value={model}
-							placeholder="Select a model"
-						/>
-
-						<datalist id="model-list">
-							{#each models as model}
-								<option value={model.name} />
-							{/each}
-						</datalist>
-					</div>
-				</div>
-			</div>
 		{/if}
 	</div>
 

src/routes/(app)/+layout.svelte

@@ -183,7 +183,6 @@
 	});
 </script>
 
-<Help />
 <SettingsModal bind:show={$showSettings} />
 <ChangelogModal bind:show={$showChangelog} />
 

src/routes/(app)/+page.svelte

@@ -1,5 +1,7 @@
 <script lang="ts">
 	import Chat from '$lib/components/chat/Chat.svelte';
+	import Help from '$lib/components/layout/Help.svelte';
 </script>
 
+<Help />
 <Chat />

src/routes/(app)/admin/+layout.svelte

@@ -30,29 +30,29 @@
 					</div>
 				</button>
 			</div>
-			<div class="flex items-center text-xl font-semibold">{$i18n.t('Workspace')}</div>
+			<div class="flex items-center text-xl font-semibold">{$i18n.t('Admin Panel')}</div>
 		</div>
 	</div>
 
-	<!-- <div class="px-4 my-1">
+	<div class="px-4 my-1">
 		<div
 			class="flex scrollbar-none overflow-x-auto w-fit text-center text-sm font-medium rounded-xl bg-transparent/10 p-1"
 		>
 			<a
-				class="min-w-fit rounded-lg p-1.5 px-3 {$page.url.pathname.includes('/workspace/models')
+				class="min-w-fit rounded-lg p-1.5 px-3 {$page.url.pathname === '/admin'
 					? 'bg-gray-50 dark:bg-gray-850'
 					: ''} transition"
-				href="/workspace/models">{$i18n.t('Models')}</a
+				href="/admin">{$i18n.t('Dashboard')}</a
 			>
 
 			<a
-				class="min-w-fit rounded-lg p-1.5 px-3 {$page.url.pathname.includes('/workspace/prompts')
+				class="min-w-fit rounded-lg p-1.5 px-3 {$page.url.pathname.includes('/admin/settings')
 					? 'bg-gray-50 dark:bg-gray-850'
 					: ''} transition"
-				href="/workspace/prompts">{$i18n.t('Prompts')}</a
+				href="/admin/settings">{$i18n.t('Settings')}</a
 			>
 
-			<a
+			<!-- <a
 				class="min-w-fit rounded-lg p-1.5 px-3 {$page.url.pathname.includes('/workspace/documents')
 					? 'bg-gray-50 dark:bg-gray-850'
 					: ''} transition"
@@ -66,9 +66,9 @@
 					? 'bg-gray-50 dark:bg-gray-850'
 					: ''} transition"
 				href="/workspace/playground">{$i18n.t('Playground')}</a
-			>
+			> -->
 		</div>
-	</div> -->
+	</div>
 
 	<hr class=" my-2 dark:border-gray-850" />
 

src/routes/(app)/admin/+page.svelte

@@ -11,12 +11,8 @@
 	import { toast } from 'svelte-sonner';
 
 	import { updateUserRole, getUsers, deleteUserById } from '$lib/apis/users';
-	import { getSignUpEnabledStatus, toggleSignUpEnabledStatus } from '$lib/apis/auths';
-
-	import MenuLines from '$lib/components/icons/MenuLines.svelte';
 
 	import EditUserModal from '$lib/components/admin/EditUserModal.svelte';
-	import SettingsModal from '$lib/components/admin/SettingsModal.svelte';
 	import Pagination from '$lib/components/common/Pagination.svelte';
 	import ChatBubbles from '$lib/components/icons/ChatBubbles.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
@@ -34,7 +30,6 @@
 
 	let page = 1;
 
-	let showSettingsModal = false;
 	let showAddUserModal = false;
 
 	let showUserChatsModal = false;
@@ -100,7 +95,6 @@
 	}}
 />
 <UserChatsModal bind:show={showUserChatsModal} user={selectedUser} />
-<SettingsModal bind:show={showSettingsModal} />
 
 {#if loaded}
 	<div class="mt-0.5 mb-3 gap-1 flex flex-col md:flex-row justify-between">
@@ -137,28 +131,6 @@
 						</svg>
 					</button>
 				</Tooltip>
-
-				<Tooltip content={$i18n.t('Admin Settings')}>
-					<button
-						class=" px-2 py-2 rounded-xl border border-gray-200 dark:border-gray-600 dark:border-0 hover:bg-gray-100 dark:bg-gray-850 dark:hover:bg-gray-800 transition font-medium text-sm flex items-center space-x-1"
-						on:click={() => {
-							showSettingsModal = !showSettingsModal;
-						}}
-					>
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path
-								fill-rule="evenodd"
-								d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
-								clip-rule="evenodd"
-							/>
-						</svg>
-					</button>
-				</Tooltip>
 			</div>
 		</div>
 	</div>

src/routes/(app)/admin/settings/+page.svelte

@@ -0,0 +1,5 @@
+<script>
+	import Settings from '$lib/components/admin/Settings.svelte';
+</script>
+
+<Settings />