feat(tts): add Doubao TTS 2.0 (Volcengine Seed-TTS 2.0) provider

components/generation/media-popover.tsx

@@ -9,8 +9,8 @@
   Mic,
   SlidersHorizontal,
   ChevronRight,
   Play,
   Loader2,
 } from 'lucide-react';
 import { toast } from 'sonner';
 import { Popover, PopoverContent, PopoverTrigger } from '@/components/ui/popover';
@@ -24,7 +24,7 @@
   SelectTrigger,
   SelectValue,
 } from '@/components/ui/select';
 import { Slider } from '@/components/ui/slider';
 import { Switch } from '@/components/ui/switch';
 import { cn } from '@/lib/utils';
 import { useI18n } from '@/lib/hooks/use-i18n';
@@ -88,6 +88,7 @@
     'azure-tts': t('settings.providerAzureTTS'),
     'glm-tts': t('settings.providerGLMTTS'),
     'qwen-tts': t('settings.providerQwenTTS'),
+    'doubao-tts': t('settings.providerDoubaoTTS'),
     'elevenlabs-tts': t('settings.providerElevenLabsTTS'),
     'browser-native-tts': t('settings.providerBrowserNativeTTS'),
   };
@@ -135,9 +136,9 @@
   const ttsVoice = useSettingsStore((s) => s.ttsVoice);
   const ttsSpeed = useSettingsStore((s) => s.ttsSpeed);
   const ttsProvidersConfig = useSettingsStore((s) => s.ttsProvidersConfig);
   const setTTSProvider = useSettingsStore((s) => s.setTTSProvider);
   const setTTSVoice = useSettingsStore((s) => s.setTTSVoice);
   const setTTSSpeed = useSettingsStore((s) => s.setTTSSpeed);
 
   const asrProviderId = useSettingsStore((s) => s.asrProviderId);
   const asrLanguage = useSettingsStore((s) => s.asrLanguage);
@@ -165,7 +166,7 @@
     needsKey: boolean,
   ) => !needsKey || !!configs[id]?.apiKey || !!configs[id]?.isServerConfigured;
 
   const ttsSpeedRange = TTS_PROVIDERS[ttsProviderId]?.speedRange;
 
   // ─── Dynamic browser voices ───
   const [browserVoices, setBrowserVoices] = useState<SpeechSynthesisVoice[]>([]);
@@ -214,7 +215,7 @@
 
   // TTS: grouped by provider, voices as items (matching Image/Video pattern)
   // Browser-native voices are split into sub-groups by language.
   const ttsGroups = useMemo(() => {
     const groups: SelectGroupData[] = [];
 
     for (const p of Object.values(TTS_PROVIDERS)) {
@@ -259,7 +260,7 @@
   }, [ttsProvidersConfig, locale, browserVoices, t]);
 
   // TTS preview
   const handlePreview = useCallback(async () => {
     if (previewing) {
       stopPreview();
       return;

components/settings/audio-settings.tsx

@@ -37,6 +37,7 @@ function getTTSProviderName(providerId: TTSProviderId, t: (key: string) => strin
     'azure-tts': t('settings.providerAzureTTS'),
     'glm-tts': t('settings.providerGLMTTS'),
     'qwen-tts': t('settings.providerQwenTTS'),
+    'doubao-tts': t('settings.providerDoubaoTTS'),
     'elevenlabs-tts': t('settings.providerElevenLabsTTS'),
     'browser-native-tts': t('settings.providerBrowserNativeTTS'),
   };

components/settings/index.tsx

@@ -121,6 +121,7 @@ function getTTSProviderName(providerId: TTSProviderId, t: (key: string) => strin
     'azure-tts': t('settings.providerAzureTTS'),
     'glm-tts': t('settings.providerGLMTTS'),
     'qwen-tts': t('settings.providerQwenTTS'),
+    'doubao-tts': t('settings.providerDoubaoTTS'),
     'elevenlabs-tts': t('settings.providerElevenLabsTTS'),
     'browser-native-tts': t('settings.providerBrowserNativeTTS'),
   };

components/settings/tts-settings.tsx

@@ -44,6 +44,23 @@ export function TTSSettings({ selectedProviderId }: TTSSettingsProps) {
   const [testMessage, setTestMessage] = useState('');
   const { previewing: testingTTS, startPreview, stopPreview } = useTTSPreview();
 
+  // Doubao TTS uses compound "appId:accessKey" — split for separate UI fields
+  const isDoubao = selectedProviderId === 'doubao-tts';
+  const rawApiKey = ttsProvidersConfig[selectedProviderId]?.apiKey || '';
+  const doubaoColonIdx = rawApiKey.indexOf(':');
+  const doubaoAppId = isDoubao && doubaoColonIdx > 0 ? rawApiKey.slice(0, doubaoColonIdx) : '';
+  const doubaoAccessKey =
+    isDoubao && doubaoColonIdx > 0
+      ? rawApiKey.slice(doubaoColonIdx + 1)
+      : isDoubao
+        ? rawApiKey
+        : '';
+
+  const setDoubaoCompoundKey = (appId: string, accessKey: string) => {
+    const combined = appId && accessKey ? `${appId}:${accessKey}` : appId || accessKey;
+    setTTSProviderConfig(selectedProviderId, { apiKey: combined });
+  };
+
   // Update test text when language changes
   useEffect(() => {
     setTestText(t('settings.ttsTestTextDefault'));
@@ -97,37 +114,93 @@ export function TTSSettings({ selectedProviderId }: TTSSettingsProps) {
       {/* API Key & Base URL */}
       {(ttsProvider.requiresApiKey || isServerConfigured) && (
         <>
-          <div className="grid grid-cols-2 gap-4">
-            <div className="space-y-2">
-              <Label className="text-sm">{t('settings.ttsApiKey')}</Label>
-              <div className="relative">
-                <Input
-                  name={`tts-api-key-${selectedProviderId}`}
-                  type={showApiKey ? 'text' : 'password'}
-                  autoComplete="new-password"
-                  autoCapitalize="none"
-                  autoCorrect="off"
-                  spellCheck={false}
-                  placeholder={
-                    isServerConfigured ? t('settings.optionalOverride') : t('settings.enterApiKey')
-                  }
-                  value={ttsProvidersConfig[selectedProviderId]?.apiKey || ''}
-                  onChange={(e) =>
-                    setTTSProviderConfig(selectedProviderId, {
-                      apiKey: e.target.value,
-                    })
-                  }
-                  className="font-mono text-sm pr-10"
-                />
-                <button
-                  type="button"
-                  onClick={() => setShowApiKey(!showApiKey)}
-                  className="absolute right-2 top-1/2 -translate-y-1/2 text-muted-foreground hover:text-foreground"
-                >
-                  {showApiKey ? <EyeOff className="h-4 w-4" /> : <Eye className="h-4 w-4" />}
-                </button>
+          <div className={cn('grid gap-4', isDoubao ? 'grid-cols-3' : 'grid-cols-2')}>
+            {isDoubao ? (
+              <>
+                <div className="space-y-2">
+                  <Label className="text-sm">App ID</Label>
+                  <div className="relative">
+                    <Input
+                      name={`tts-app-id-${selectedProviderId}`}
+                      type={showApiKey ? 'text' : 'password'}
+                      autoComplete="new-password"
+                      autoCapitalize="none"
+                      autoCorrect="off"
+                      spellCheck={false}
+                      placeholder={
+                        isServerConfigured
+                          ? t('settings.optionalOverride')
+                          : t('settings.enterApiKey')
+                      }
+                      value={doubaoAppId}
+                      onChange={(e) => setDoubaoCompoundKey(e.target.value, doubaoAccessKey)}
+                      className="font-mono text-sm pr-10"
+                    />
+                    <button
+                      type="button"
+                      onClick={() => setShowApiKey(!showApiKey)}
+                      className="absolute right-2 top-1/2 -translate-y-1/2 text-muted-foreground hover:text-foreground"
+                    >
+                      {showApiKey ? <EyeOff className="h-4 w-4" /> : <Eye className="h-4 w-4" />}
+                    </button>
+                  </div>
+                </div>
+                <div className="space-y-2">
+                  <Label className="text-sm">Access Key</Label>
+                  <div className="relative">
+                    <Input
+                      name={`tts-access-key-${selectedProviderId}`}
+                      type={showApiKey ? 'text' : 'password'}
+                      autoComplete="new-password"
+                      autoCapitalize="none"
+                      autoCorrect="off"
+                      spellCheck={false}
+                      placeholder={
+                        isServerConfigured
+                          ? t('settings.optionalOverride')
+                          : t('settings.enterApiKey')
+                      }
+                      value={doubaoAccessKey}
+                      onChange={(e) => setDoubaoCompoundKey(doubaoAppId, e.target.value)}
+                      className="font-mono text-sm"
+                    />
+                  </div>
+                </div>
+              </>
+            ) : (
+              <div className="space-y-2">
+                <Label className="text-sm">{t('settings.ttsApiKey')}</Label>
+                <div className="relative">
+                  <Input
+                    name={`tts-api-key-${selectedProviderId}`}
+                    type={showApiKey ? 'text' : 'password'}
+                    autoComplete="new-password"
+                    autoCapitalize="none"
+                    autoCorrect="off"
+                    spellCheck={false}
+                    placeholder={
+                      isServerConfigured
+                        ? t('settings.optionalOverride')
+                        : t('settings.enterApiKey')
+                    }
+                    value={ttsProvidersConfig[selectedProviderId]?.apiKey || ''}
+                    onChange={(e) =>
+                      setTTSProviderConfig(selectedProviderId, {
+                        apiKey: e.target.value,
+                      })
+                    }
+                    className="font-mono text-sm pr-10"
+                  />
+                  <button
+                    type="button"
+                    onClick={() => setShowApiKey(!showApiKey)}
+                    className="absolute right-2 top-1/2 -translate-y-1/2 text-muted-foreground hover:text-foreground"
+                  >
+                    {showApiKey ? <EyeOff className="h-4 w-4" /> : <Eye className="h-4 w-4" />}
+                  </button>
+                </div>
               </div>
-            </div>
+            )}
             <div className="space-y-2">
               <Label className="text-sm">{t('settings.ttsBaseUrl')}</Label>
               <Input
@@ -167,6 +240,9 @@ export function TTSSettings({ selectedProviderId }: TTSSettingsProps) {
               case 'elevenlabs-tts':
                 endpointPath = '/text-to-speech';
                 break;
+              case 'doubao-tts':
+                endpointPath = '/unidirectional';
+                break;
             }
             if (!endpointPath) return null;
             return (

lib/audio/constants.ts

@@ -606,6 +606,105 @@ export const TTS_PROVIDERS: Record<TTSProviderId, TTSProviderConfig> = {
     supportedFormats: ['mp3', 'wav', 'pcm'],
   },
 
+  'doubao-tts': {
+    id: 'doubao-tts',
+    name: '豆包 TTS 2.0（火山引擎）',
+    requiresApiKey: true,
+    defaultBaseUrl: 'https://openspeech.bytedance.com/api/v3/tts',
+    icon: '/logos/doubao.svg',
+    voices: [
+      { id: 'zh_female_vv_uranus_bigtts', name: 'Vivi 2.0', language: 'zh-CN', gender: 'female' },
+      {
+        id: 'zh_female_xiaohe_uranus_bigtts',
+        name: '小何 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_male_m191_uranus_bigtts',
+        name: '云舟 2.0',
+        language: 'zh-CN',
+        gender: 'male',
+      },
+      {
+        id: 'zh_male_taocheng_uranus_bigtts',
+        name: '小天 2.0',
+        language: 'zh-CN',
+        gender: 'male',
+      },
+      {
+        id: 'zh_male_liufei_uranus_bigtts',
+        name: '刘飞 2.0',
+        language: 'zh-CN',
+        gender: 'male',
+      },
+      {
+        id: 'zh_female_qingxinnvsheng_uranus_bigtts',
+        name: '清新女声 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_female_cancan_uranus_bigtts',
+        name: '知性灿灿 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_female_shuangkuaisisi_uranus_bigtts',
+        name: '爽快思思 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_female_tianmeixiaoyuan_uranus_bigtts',
+        name: '甜美小源 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_female_linjianvhai_uranus_bigtts',
+        name: '邻家女孩 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_male_shaonianzixin_uranus_bigtts',
+        name: '少年梓辛 2.0',
+        language: 'zh-CN',
+        gender: 'male',
+      },
+      {
+        id: 'zh_male_ruyayichen_uranus_bigtts',
+        name: '儒雅逸辰 2.0',
+        language: 'zh-CN',
+        gender: 'male',
+      },
+      {
+        id: 'zh_female_yingyujiaoxue_uranus_bigtts',
+        name: 'Tina老师 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      {
+        id: 'zh_female_kefunvsheng_uranus_bigtts',
+        name: '暖阳女声 2.0',
+        language: 'zh-CN',
+        gender: 'female',
+      },
+      { id: 'en_male_tim_uranus_bigtts', name: 'Tim', language: 'en-US', gender: 'male' },
+      { id: 'en_female_dacey_uranus_bigtts', name: 'Dacey', language: 'en-US', gender: 'female' },
+      {
+        id: 'en_female_stokie_uranus_bigtts',
+        name: 'Stokie',
+        language: 'en-US',
+        gender: 'female',
+      },
+    ],
+    supportedFormats: ['mp3', 'ogg_opus', 'pcm'],
+    speedRange: { min: 0.5, max: 2.0, default: 1.0 },
+  },
+
   'elevenlabs-tts': {
     id: 'elevenlabs-tts',
     name: 'ElevenLabs TTS',
@@ -895,6 +994,7 @@ export const DEFAULT_TTS_VOICES: Record<TTSProviderId, string> = {
   'azure-tts': 'zh-CN-XiaoxiaoNeural',
   'glm-tts': 'tongtong',
   'qwen-tts': 'Cherry',
+  'doubao-tts': 'zh_female_vv_uranus_bigtts',
   'elevenlabs-tts': 'EXAVITQu4vr4xnSDxMaL',
   'browser-native-tts': 'default',
 };