refac/enh: openai tts additional params support

backend/open_webui/config.py

@@ -3361,6 +3361,19 @@ AUDIO_TTS_OPENAI_API_KEY = PersistentConfig(
     os.getenv("AUDIO_TTS_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+audio_tts_openai_params = os.getenv("AUDIO_TTS_OPENAI_PARAMS", "")
+try:
+    audio_tts_openai_params = json.loads(audio_tts_openai_params)
+except json.JSONDecodeError:
+    audio_tts_openai_params = {}
+
+AUDIO_TTS_OPENAI_PARAMS = PersistentConfig(
+    "AUDIO_TTS_OPENAI_PARAMS",
+    "audio.tts.openai.params",
+    audio_tts_openai_params,
+)
+
+
 AUDIO_TTS_API_KEY = PersistentConfig(
     "AUDIO_TTS_API_KEY",
     "audio.tts.api_key",

backend/open_webui/main.py

@@ -175,13 +175,14 @@ from open_webui.config import (
     AUDIO_STT_AZURE_LOCALES,
     AUDIO_STT_AZURE_BASE_URL,
     AUDIO_STT_AZURE_MAX_SPEAKERS,
-    AUDIO_TTS_API_KEY,
     AUDIO_TTS_ENGINE,
     AUDIO_TTS_MODEL,
+    AUDIO_TTS_VOICE,
     AUDIO_TTS_OPENAI_API_BASE_URL,
     AUDIO_TTS_OPENAI_API_KEY,
+    AUDIO_TTS_OPENAI_PARAMS,
+    AUDIO_TTS_API_KEY,
     AUDIO_TTS_SPLIT_ON,
-    AUDIO_TTS_VOICE,
     AUDIO_TTS_AZURE_SPEECH_REGION,
     AUDIO_TTS_AZURE_SPEECH_BASE_URL,
     AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT,
@@ -1096,11 +1097,15 @@ app.state.config.AUDIO_STT_AZURE_LOCALES = AUDIO_STT_AZURE_LOCALES
 app.state.config.AUDIO_STT_AZURE_BASE_URL = AUDIO_STT_AZURE_BASE_URL
 app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS = AUDIO_STT_AZURE_MAX_SPEAKERS
 
-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
+
+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_OPENAI_PARAMS = AUDIO_TTS_OPENAI_PARAMS
+
 app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
 app.state.config.TTS_SPLIT_ON = AUDIO_TTS_SPLIT_ON
 

backend/open_webui/routers/audio.py

@@ -154,6 +154,7 @@ def set_faster_whisper_model(model: str, auto_update: bool = False):
 class TTSConfigForm(BaseModel):
     OPENAI_API_BASE_URL: str
     OPENAI_API_KEY: str
+    OPENAI_PARAMS: Optional[dict] = None
     API_KEY: str
     ENGINE: str
     MODEL: str
@@ -190,6 +191,7 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)):
         "tts": {
             "OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
             "OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
+            "OPENAI_PARAMS": request.app.state.config.TTS_OPENAI_PARAMS,
             "API_KEY": request.app.state.config.TTS_API_KEY,
             "ENGINE": request.app.state.config.TTS_ENGINE,
             "MODEL": request.app.state.config.TTS_MODEL,
@@ -222,6 +224,7 @@ async def update_audio_config(
 ):
     request.app.state.config.TTS_OPENAI_API_BASE_URL = form_data.tts.OPENAI_API_BASE_URL
     request.app.state.config.TTS_OPENAI_API_KEY = form_data.tts.OPENAI_API_KEY
+    request.app.state.config.TTS_OPENAI_PARAMS = form_data.tts.OPENAI_PARAMS
     request.app.state.config.TTS_API_KEY = form_data.tts.API_KEY
     request.app.state.config.TTS_ENGINE = form_data.tts.ENGINE
     request.app.state.config.TTS_MODEL = form_data.tts.MODEL
@@ -262,12 +265,13 @@ async def update_audio_config(
 
     return {
         "tts": {
-            "OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
-            "OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
-            "API_KEY": request.app.state.config.TTS_API_KEY,
             "ENGINE": request.app.state.config.TTS_ENGINE,
             "MODEL": request.app.state.config.TTS_MODEL,
             "VOICE": request.app.state.config.TTS_VOICE,
+            "OPENAI_API_BASE_URL": request.app.state.config.TTS_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": request.app.state.config.TTS_OPENAI_API_KEY,
+            "OPENAI_PARAMS": request.app.state.config.TTS_OPENAI_PARAMS,
+            "API_KEY": request.app.state.config.TTS_API_KEY,
             "SPLIT_ON": request.app.state.config.TTS_SPLIT_ON,
             "AZURE_SPEECH_REGION": request.app.state.config.TTS_AZURE_SPEECH_REGION,
             "AZURE_SPEECH_BASE_URL": request.app.state.config.TTS_AZURE_SPEECH_BASE_URL,
@@ -337,6 +341,11 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             async with aiohttp.ClientSession(
                 timeout=timeout, trust_env=True
             ) as session:
+                payload = {
+                    **payload,
+                    **(request.app.state.config.TTS_OPENAI_PARAMS or {}),
+                }
+
                 r = await session.post(
                     url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
                     json=payload,

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

@@ -19,6 +19,7 @@
 
 	import type { Writable } from 'svelte/store';
 	import type { i18n as i18nType } from 'i18next';
+	import Textarea from '$lib/components/common/Textarea.svelte';
 
 	const i18n = getContext<Writable<i18nType>>('i18n');
 
@@ -31,6 +32,7 @@
 	let TTS_ENGINE = '';
 	let TTS_MODEL = '';
 	let TTS_VOICE = '';
+	let TTS_OPENAI_PARAMS = '';
 	let TTS_SPLIT_ON: TTS_RESPONSE_SPLIT = TTS_RESPONSE_SPLIT.PUNCTUATION;
 	let TTS_AZURE_SPEECH_REGION = '';
 	let TTS_AZURE_SPEECH_BASE_URL = '';
@@ -98,18 +100,28 @@
 	};
 
 	const updateConfigHandler = async () => {
+		let openaiParams = {};
+		try {
+			openaiParams = TTS_OPENAI_PARAMS ? JSON.parse(TTS_OPENAI_PARAMS) : {};
+			TTS_OPENAI_PARAMS = JSON.stringify(openaiParams, null, 2);
+		} catch (e) {
+			toast.error($i18n.t('Invalid JSON format for Parameters'));
+			return;
+		}
+
 		const res = await updateAudioConfig(localStorage.token, {
 			tts: {
 				OPENAI_API_BASE_URL: TTS_OPENAI_API_BASE_URL,
 				OPENAI_API_KEY: TTS_OPENAI_API_KEY,
+				OPENAI_PARAMS: openaiParams,
 				API_KEY: TTS_API_KEY,
 				ENGINE: TTS_ENGINE,
 				MODEL: TTS_MODEL,
 				VOICE: TTS_VOICE,
-				SPLIT_ON: TTS_SPLIT_ON,
 				AZURE_SPEECH_REGION: TTS_AZURE_SPEECH_REGION,
 				AZURE_SPEECH_BASE_URL: TTS_AZURE_SPEECH_BASE_URL,
-				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT
+				AZURE_SPEECH_OUTPUT_FORMAT: TTS_AZURE_SPEECH_OUTPUT_FORMAT,
+				SPLIT_ON: TTS_SPLIT_ON
 			},
 			stt: {
 				OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
@@ -146,6 +158,7 @@
 			console.log(res);
 			TTS_OPENAI_API_BASE_URL = res.tts.OPENAI_API_BASE_URL;
 			TTS_OPENAI_API_KEY = res.tts.OPENAI_API_KEY;
+			TTS_OPENAI_PARAMS = JSON.stringify(res?.tts?.OPENAI_PARAMS ?? '', null, 2);
 			TTS_API_KEY = res.tts.API_KEY;
 
 			TTS_ENGINE = res.tts.ENGINE;
@@ -612,6 +625,22 @@
 								</div>
 							</div>
 						</div>
+
+						<div class="mt-2 mb-1 text-xs text-gray-400 dark:text-gray-500">
+							<div class="w-full">
+								<div class=" mb-1.5 text-xs font-medium">{$i18n.t('Additional Parameters')}</div>
+								<div class="flex w-full">
+									<div class="flex-1">
+										<Textarea
+											className="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-hidden"
+											bind:value={TTS_OPENAI_PARAMS}
+											placeholder={$i18n.t('Enter additional parameters')}
+											minSize={100}
+										/>
+									</div>
+								</div>
+							</div>
+						</div>
 					{:else if TTS_ENGINE === 'elevenlabs'}
 						<div class=" flex gap-2">
 							<div class="w-full">