diff --git a/src/main/presenter/agentRuntimePresenter/index.ts b/src/main/presenter/agentRuntimePresenter/index.ts
index ac7198b10..73dc22488 100644
--- a/src/main/presenter/agentRuntimePresenter/index.ts
+++ b/src/main/presenter/agentRuntimePresenter/index.ts
@@ -58,6 +58,7 @@ import {
   supportsOpenAIImageGenerationSettings
 } from '@shared/imageGenerationSettings'
 import { isDeepSeekSeriesModelId } from '@shared/model'
+import { isTtsModelConfig, isTtsModelId } from '@shared/ttsSettings'
 import { nanoid } from 'nanoid'
 import type { SQLitePresenter } from '../sqlitePresenter'
 import { eventBus, SendTarget } from '@/eventbus'
@@ -1963,6 +1964,9 @@ export class AgentRuntimePresenter implements IAgentImplementation {
           try {
             let providerMessages = injectedMessages
             let providerMaxTokens = requestMaxTokens
+            const isTtsRequest =
+              isTtsModelConfig(requestModelConfig) || isTtsModelId(requestModelId)
+            const effectiveRequestTools: MCPToolDefinition[] = isTtsRequest ? [] : requestTools
 
             if (!bypassContextBudget) {
               const protectedSteerTailCount =
@@ -1971,7 +1975,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
                   : 0
               let requestPreflight = preflightRequestContext({
                 messages: injectedMessages,
-                tools: requestTools,
+                tools: effectiveRequestTools,
                 contextLength: requestModelConfig.contextLength,
                 requestedMaxTokens: requestMaxTokens,
                 minimumProtectedTailCount: protectedSteerTailCount
@@ -1988,7 +1992,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
                   baseSystemPrompt,
                   contextLength: requestModelConfig.contextLength,
                   requestedMaxTokens: requestPreflight.requestedMaxTokens,
-                  tools: requestTools,
+                  tools: effectiveRequestTools,
                   supportsVision,
                   supportsAudioInput,
                   interleavedReasoning,
@@ -2001,7 +2005,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
                 }
                 requestPreflight = preflightRequestContext({
                   messages: requestMessages,
-                  tools: requestTools,
+                  tools: effectiveRequestTools,
                   contextLength: requestModelConfig.contextLength,
                   requestedMaxTokens: requestMaxTokens,
                   minimumProtectedTailCount: protectedSteerTailCount
@@ -2041,7 +2045,7 @@ export class AgentRuntimePresenter implements IAgentImplementation {
               requestModelConfig,
               requestTemperature,
               providerMaxTokens,
-              requestTools
+              effectiveRequestTools
             )) {
               if (!didConsumeSteerBatch && claimedSteerBatch.length > 0) {
                 pendingInputCoordinator.consumeClaimedSteerBatch(sessionId)
diff --git a/src/main/presenter/llmProviderPresenter/aiSdk/runtime.ts b/src/main/presenter/llmProviderPresenter/aiSdk/runtime.ts
index 84d7ce9e3..8ae3b368c 100644
--- a/src/main/presenter/llmProviderPresenter/aiSdk/runtime.ts
+++ b/src/main/presenter/llmProviderPresenter/aiSdk/runtime.ts
@@ -32,6 +32,8 @@ import type { LLMCoreStreamEvent } from '@shared/types/core/llm-events'
 import { mcpToolsToAISDKTools } from './toolMapper'
 import { mapMessagesToModelMessages } from './messageMapper'
 import { buildProviderOptions } from './providerOptionsMapper'
+import { ProxyAgent } from 'undici'
+import { proxyConfig } from '../../proxyConfig'
 import { type AiSdkProviderKind, createAiSdkProviderContext } from './providerFactory'
 import { adaptAiSdkStream } from './streamAdapter'
 
@@ -228,9 +230,11 @@ async function executeTtsPatternA(
 
   const controller = new AbortController()
   const timeoutId = timeout ? setTimeout(() => controller.abort(), timeout) : undefined
+  const proxyUrl = proxyConfig.getProxyUrl()
+  const dispatcher = proxyUrl ? new ProxyAgent(proxyUrl) : undefined
 
   try {
-    const response = await fetch(url, {
+    const fetchInit: RequestInit & { dispatcher?: ProxyAgent } = {
       method: 'POST',
       headers: {
         ...defaultHeaders,
@@ -239,7 +243,9 @@ async function executeTtsPatternA(
       },
       body: JSON.stringify(body),
       signal: controller.signal
-    })
+    }
+    if (dispatcher) fetchInit.dispatcher = dispatcher
+    const response = await fetch(url, fetchInit)
 
     if (!response.ok) {
       const errText = await response.text().catch(() => '')
@@ -283,9 +289,11 @@ async function executeTtsPatternB(
 
   const controller = new AbortController()
   const timeoutId = timeout ? setTimeout(() => controller.abort(), timeout) : undefined
+  const proxyUrl = proxyConfig.getProxyUrl()
+  const dispatcher = proxyUrl ? new ProxyAgent(proxyUrl) : undefined
 
   try {
-    const response = await fetch(url, {
+    const fetchInit: RequestInit & { dispatcher?: ProxyAgent } = {
       method: 'POST',
       headers: {
         ...defaultHeaders,
@@ -294,7 +302,9 @@ async function executeTtsPatternB(
       },
       body: JSON.stringify(body),
       signal: controller.signal
-    })
+    }
+    if (dispatcher) fetchInit.dispatcher = dispatcher
+    const response = await fetch(url, fetchInit)
 
     if (!response.ok) {
       const errText = await response.text().catch(() => '')
diff --git a/src/renderer/settings/components/ProviderModelList.vue b/src/renderer/settings/components/ProviderModelList.vue
index c970888d8..d4b45ff76 100644
--- a/src/renderer/settings/components/ProviderModelList.vue
+++ b/src/renderer/settings/components/ProviderModelList.vue
@@ -453,7 +453,7 @@ const hasModelCapability = (model: RENDERER_MODEL_META, capability: ModelCapabil
 
 const getModelTypeLabel = (type: ModelType) => {
   if (type === ModelType.TTS) {
-    return t('settings.provider.voiceai.title')
+    return t('settings.provider.tts.title')
   }
   return t(`model.filter.typeOptions.${type}`)
 }
diff --git a/src/renderer/settings/components/VoiceAIProviderConfig.vue b/src/renderer/settings/components/VoiceAIProviderConfig.vue
index 8cdb2a3a8..6483142c3 100644
--- a/src/renderer/settings/components/VoiceAIProviderConfig.vue
+++ b/src/renderer/settings/components/VoiceAIProviderConfig.vue
@@ -6,9 +6,9 @@
           <Icon icon="lucide:audio-waveform" class="h-5 w-5" />
         </div>
         <div class="space-y-1">
-          <p class="text-sm font-medium">{{ t('settings.provider.voiceai.title') }}</p>
+          <p class="text-sm font-medium">{{ t('settings.provider.tts.title') }}</p>
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.description') }}
+            {{ t('settings.provider.tts.description') }}
           </p>
         </div>
       </div>
@@ -18,11 +18,11 @@
       <div class="grid gap-4 md:grid-cols-2">
         <div class="space-y-2">
           <Label :for="`${provider.id}-audio-format`" class="text-xs font-medium">
-            {{ t('settings.provider.voiceai.audioFormat.label') }}
+            {{ t('settings.provider.tts.audioFormat.label') }}
           </Label>
           <Select v-model="audioFormat" :disabled="isHydrating">
             <SelectTrigger :id="`${provider.id}-audio-format`">
-              <SelectValue :placeholder="t('settings.provider.voiceai.audioFormat.placeholder')" />
+              <SelectValue :placeholder="t('settings.provider.tts.audioFormat.placeholder')" />
             </SelectTrigger>
             <SelectContent>
               <SelectItem value="mp3">MP3</SelectItem>
@@ -31,17 +31,17 @@
             </SelectContent>
           </Select>
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.audioFormat.helper') }}
+            {{ t('settings.provider.tts.audioFormat.helper') }}
           </p>
         </div>
 
         <div class="space-y-2">
           <Label :for="`${provider.id}-language`" class="text-xs font-medium">
-            {{ t('settings.provider.voiceai.language.label') }}
+            {{ t('settings.provider.tts.language.label') }}
           </Label>
           <Select v-model="language" :disabled="isHydrating">
             <SelectTrigger :id="`${provider.id}-language`">
-              <SelectValue :placeholder="t('settings.provider.voiceai.language.placeholder')" />
+              <SelectValue :placeholder="t('settings.provider.tts.language.placeholder')" />
             </SelectTrigger>
             <SelectContent>
               <SelectItem
@@ -54,37 +54,37 @@
             </SelectContent>
           </Select>
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.language.helper') }}
+            {{ t('settings.provider.tts.language.helper') }}
           </p>
         </div>
 
         <div class="space-y-2 md:col-span-2">
           <Label :for="`${provider.id}-tts-model`" class="text-xs font-medium">
-            {{ t('settings.provider.voiceai.model.label') }}
+            {{ t('settings.provider.tts.model.label') }}
           </Label>
           <Input
             :id="`${provider.id}-tts-model`"
             v-model="ttsModel"
-            :placeholder="t('settings.provider.voiceai.model.placeholder')"
+            :placeholder="t('settings.provider.tts.model.placeholder')"
             :disabled="isHydrating"
           />
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.model.helper') }}
+            {{ t('settings.provider.tts.model.helper') }}
           </p>
         </div>
 
         <div class="space-y-2 md:col-span-2">
           <Label :for="`${provider.id}-agent-id`" class="text-xs font-medium">
-            {{ t('settings.provider.voiceai.agentId.label') }}
+            {{ t('settings.provider.tts.agentId.label') }}
           </Label>
           <Input
             :id="`${provider.id}-agent-id`"
             v-model="agentId"
-            :placeholder="t('settings.provider.voiceai.agentId.placeholder')"
+            :placeholder="t('settings.provider.tts.agentId.placeholder')"
             :disabled="isHydrating"
           />
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.agentId.helper') }}
+            {{ t('settings.provider.tts.agentId.helper') }}
           </p>
         </div>
       </div>
@@ -95,7 +95,7 @@
         <div class="space-y-2">
           <div class="flex items-center justify-between">
             <Label :for="`${provider.id}-temperature`" class="text-xs font-medium">
-              {{ t('settings.provider.voiceai.temperature.label') }}
+              {{ t('settings.provider.tts.temperature.label') }}
             </Label>
             <span class="text-xs text-muted-foreground">{{ temperature.toFixed(2) }}</span>
           </div>
@@ -108,14 +108,14 @@
             @update:model-value="onTemperatureChange"
           />
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.temperature.helper') }}
+            {{ t('settings.provider.tts.temperature.helper') }}
           </p>
         </div>
 
         <div class="space-y-2">
           <div class="flex items-center justify-between">
             <Label :for="`${provider.id}-top-p`" class="text-xs font-medium">
-              {{ t('settings.provider.voiceai.topP.label') }}
+              {{ t('settings.provider.tts.topP.label') }}
             </Label>
             <span class="text-xs text-muted-foreground">{{ topP.toFixed(2) }}</span>
           </div>
@@ -128,7 +128,7 @@
             @update:model-value="onTopPChange"
           />
           <p class="text-xs text-muted-foreground">
-            {{ t('settings.provider.voiceai.topP.helper') }}
+            {{ t('settings.provider.tts.topP.helper') }}
           </p>
         </div>
       </div>
diff --git a/src/renderer/src/components/chat/ChatStatusBar.vue b/src/renderer/src/components/chat/ChatStatusBar.vue
index dc79db218..8d7612cc0 100644
--- a/src/renderer/src/components/chat/ChatStatusBar.vue
+++ b/src/renderer/src/components/chat/ChatStatusBar.vue
@@ -103,12 +103,6 @@
                 :is-dark="themeStore.isDark"
               />
               <span>{{ displayModelText }}</span>
-              <Icon
-                v-if="capabilitySupportsAudioInput === true"
-                icon="lucide:mic"
-                class="h-3 w-3 text-emerald-500"
-                :title="t('chat.modelPicker.audioInputSupported')"
-              />
               <Icon
                 v-if="showModelOptionsLoading"
                 icon="lucide:loader-2"
@@ -1065,7 +1059,6 @@ const numericInputErrors = ref<
 })
 
 const capabilitySupportsReasoning = ref<boolean | null>(null)
-const capabilitySupportsAudioInput = ref<boolean | null>(null)
 const capabilityReasoningPortrait = ref<ReasoningPortrait | null>(null)
 const capabilitySupportsTemperature = ref<boolean | null>(null)
 const capabilityProviderId = ref('')
@@ -2103,7 +2096,6 @@ const fetchCapabilities = async (providerId: string, modelId: string): Promise<v
       modelId,
       modelConfig.endpointType
     )
-    capabilitySupportsAudioInput.value = capabilities.supportsAudioInput
     const portrait = capabilities.reasoningPortrait ?? null
 
     capabilityReasoningPortrait.value = portrait
@@ -2116,7 +2108,6 @@ const fetchCapabilities = async (providerId: string, modelId: string): Promise<v
   } catch (error) {
     console.warn('[ChatStatusBar] Failed to fetch model capabilities:', error)
     capabilityProviderId.value = providerId
-    capabilitySupportsAudioInput.value = null
     capabilitySupportsReasoning.value = null
     capabilityReasoningPortrait.value = null
     capabilitySupportsTemperature.value = null
@@ -2240,7 +2231,6 @@ const syncGenerationSettings = async () => {
     localSettings.value = null
     loadedSettingsSelection.value = null
     capabilityProviderId.value = ''
-    capabilitySupportsAudioInput.value = null
     capabilitySupportsReasoning.value = null
     capabilityReasoningPortrait.value = null
     return
@@ -2251,7 +2241,6 @@ const syncGenerationSettings = async () => {
     localSettings.value = null
     loadedSettingsSelection.value = null
     capabilityProviderId.value = ''
-    capabilitySupportsAudioInput.value = null
     capabilityReasoningPortrait.value = null
     capabilitySupportsReasoning.value = null
     return
diff --git a/src/renderer/src/components/settings/ModelConfigDialog.vue b/src/renderer/src/components/settings/ModelConfigDialog.vue
index d87fdc3b0..71eaed14f 100644
--- a/src/renderer/src/components/settings/ModelConfigDialog.vue
+++ b/src/renderer/src/components/settings/ModelConfigDialog.vue
@@ -177,7 +177,7 @@
                   {{ t('settings.model.modelConfig.type.options.imageGeneration') }}
                 </SelectItem>
                 <SelectItem value="tts">
-                  {{ t('settings.provider.voiceai.title') }}
+                  {{ t('settings.provider.tts.title') }}
                 </SelectItem>
               </SelectContent>
             </Select>
@@ -241,7 +241,7 @@
                   {{ t('settings.model.modelConfig.apiEndpoint.options.image') }}
                 </SelectItem>
                 <SelectItem value="audio-speech">
-                  {{ t('settings.provider.voiceai.title') }}
+                  {{ t('settings.provider.tts.title') }}
                 </SelectItem>
               </SelectContent>
             </Select>
diff --git a/src/renderer/src/components/settings/TtsSettingsFields.vue b/src/renderer/src/components/settings/TtsSettingsFields.vue
index 8a7a40204..93144525d 100644
--- a/src/renderer/src/components/settings/TtsSettingsFields.vue
+++ b/src/renderer/src/components/settings/TtsSettingsFields.vue
@@ -1,29 +1,29 @@
 <template>
   <div class="space-y-4">
     <div class="space-y-2">
-      <Label>{{ t('settings.provider.voiceai.title') }}</Label>
+      <Label>{{ t('settings.provider.tts.title') }}</Label>
       <p class="text-xs text-muted-foreground">
-        {{ t('settings.provider.voiceai.description') }}
+        {{ t('settings.provider.tts.description') }}
       </p>
     </div>
 
     <div class="space-y-2">
-      <Label>{{ t('settings.provider.voiceai.agentId.label') }}</Label>
+      <Label>{{ t('settings.provider.tts.agentId.label') }}</Label>
       <Input
         :model-value="tts.voice ?? ''"
-        :placeholder="t('settings.provider.voiceai.agentId.placeholder')"
+        :placeholder="t('settings.provider.tts.agentId.placeholder')"
         @update:model-value="onVoiceInput"
       />
     </div>
 
     <div class="space-y-2">
-      <Label>{{ t('settings.provider.voiceai.audioFormat.label') }}</Label>
+      <Label>{{ t('settings.provider.tts.audioFormat.label') }}</Label>
       <Select
         :model-value="optionSelectValue(tts.responseFormat)"
         @update:model-value="onResponseFormatSelect"
       >
         <SelectTrigger>
-          <SelectValue :placeholder="t('settings.provider.voiceai.audioFormat.placeholder')" />
+          <SelectValue :placeholder="t('settings.provider.tts.audioFormat.placeholder')" />
         </SelectTrigger>
         <SelectContent>
           <SelectItem :value="DEFAULT_SELECT_VALUE">
@@ -37,7 +37,7 @@
     </div>
 
     <div class="space-y-2">
-      <Label>{{ t('settings.provider.voiceai.temperature.label') }}</Label>
+      <Label>{{ t('settings.provider.tts.temperature.label') }}</Label>
       <Input
         :model-value="speedDraft"
         inputmode="decimal"
@@ -47,7 +47,7 @@
         @keydown.enter.prevent="commitSpeed"
       />
       <p class="text-xs text-muted-foreground">
-        {{ t('settings.provider.voiceai.temperature.helper') }}
+        {{ t('settings.provider.tts.temperature.helper') }}
       </p>
     </div>
 
diff --git a/src/renderer/src/i18n/da-DK/settings.json b/src/renderer/src/i18n/da-DK/settings.json
index 89ae919c9..756c81cd1 100644
--- a/src/renderer/src/i18n/da-DK/settings.json
+++ b/src/renderer/src/i18n/da-DK/settings.json
@@ -579,8 +579,8 @@
     "stopModel": "Stop model",
     "pulling": "Henter...",
     "runModel": "Kør model",
-    "voiceai": {
-      "title": "Voice.ai tekst-til-tale",
+    "tts": {
+      "title": "Tekst-til-tale (TTS)",
       "description": "Generér tale fra tekst. Stemmer vises i modellisten nedenfor.",
       "audioFormat": {
         "label": "Lydformat",
diff --git a/src/renderer/src/i18n/en-US/settings.json b/src/renderer/src/i18n/en-US/settings.json
index 626c306db..257d32b63 100644
--- a/src/renderer/src/i18n/en-US/settings.json
+++ b/src/renderer/src/i18n/en-US/settings.json
@@ -907,8 +907,8 @@
       "verifyFailed": "Verification failed",
       "verifySuccess": "Verification is successful"
     },
-    "voiceai": {
-      "title": "Voice.ai Text-to-Speech",
+    "tts": {
+      "title": "Text-to-Speech (TTS)",
       "description": "Generate speech from text. Voices appear in the model list below.",
       "audioFormat": {
         "label": "Audio Format",
diff --git a/src/renderer/src/i18n/fa-IR/settings.json b/src/renderer/src/i18n/fa-IR/settings.json
index 714ceb738..8e23128c4 100644
--- a/src/renderer/src/i18n/fa-IR/settings.json
+++ b/src/renderer/src/i18n/fa-IR/settings.json
@@ -658,8 +658,8 @@
     "stopModel": "ایست مدل",
     "pulling": "در حال دریافت...",
     "runModel": "اجرای مدل",
-    "voiceai": {
-      "title": "تبدیل متن به گفتار Voice.ai",
+    "tts": {
+      "title": "تبدیل متن به گفتار (TTS)",
       "description": "گفتار را از متن تولید کنید. صداها در فهرست مدل‌ها در پایین نمایش داده می‌شوند.",
       "audioFormat": {
         "label": "قالب صوتی",
diff --git a/src/renderer/src/i18n/fr-FR/settings.json b/src/renderer/src/i18n/fr-FR/settings.json
index 05ea8be84..62eb66d15 100644
--- a/src/renderer/src/i18n/fr-FR/settings.json
+++ b/src/renderer/src/i18n/fr-FR/settings.json
@@ -658,8 +658,8 @@
     "stopModel": "Arrêter le modèle",
     "pulling": "Récupération...",
     "runModel": "Exécuter le modèle",
-    "voiceai": {
-      "title": "Synthèse vocale Voice.ai",
+    "tts": {
+      "title": "Synthese vocale (TTS)",
       "description": "Générez de la parole à partir du texte. Les voix apparaissent dans la liste des modèles ci-dessous.",
       "audioFormat": {
         "label": "Format audio",
diff --git a/src/renderer/src/i18n/he-IL/settings.json b/src/renderer/src/i18n/he-IL/settings.json
index 78f5abf85..706a00361 100644
--- a/src/renderer/src/i18n/he-IL/settings.json
+++ b/src/renderer/src/i18n/he-IL/settings.json
@@ -658,8 +658,8 @@
     "stopModel": "עצור מודל",
     "pulling": "מושך...",
     "runModel": "הרץ מודל",
-    "voiceai": {
-      "title": "המרת טקסט לדיבור של Voice.ai",
+    "tts": {
+      "title": "המרת טקסט לדיבור (TTS)",
       "description": "יצירת דיבור מטקסט. קולות יופיעו ברשימת המודלים למטה.",
       "audioFormat": {
         "label": "פורמט שמע",
diff --git a/src/renderer/src/i18n/ja-JP/settings.json b/src/renderer/src/i18n/ja-JP/settings.json
index d92d84a59..4a7e21972 100644
--- a/src/renderer/src/i18n/ja-JP/settings.json
+++ b/src/renderer/src/i18n/ja-JP/settings.json
@@ -658,8 +658,8 @@
     "stopModel": "モデルを停止",
     "pulling": "取得中...",
     "runModel": "モデルを実行",
-    "voiceai": {
-      "title": "Voice.ai テキスト読み上げ",
+    "tts": {
+      "title": "テキスト読み上げ (TTS)",
       "description": "テキストから音声を生成します。音声は下のモデル一覧に表示されます。",
       "audioFormat": {
         "label": "音声形式",
diff --git a/src/renderer/src/i18n/ko-KR/settings.json b/src/renderer/src/i18n/ko-KR/settings.json
index c5da7b286..45d080ee2 100644
--- a/src/renderer/src/i18n/ko-KR/settings.json
+++ b/src/renderer/src/i18n/ko-KR/settings.json
@@ -652,8 +652,8 @@
     "stopModel": "모델 중지",
     "pulling": "가져오는 중...",
     "runModel": "모델 실행",
-    "voiceai": {
-      "title": "Voice.ai 텍스트 음성 변환",
+    "tts": {
+      "title": "텍스트 음성 변환 (TTS)",
       "description": "텍스트로부터 음성을 생성합니다. 음성은 아래 모델 목록에 표시됩니다.",
       "audioFormat": {
         "label": "오디오 형식",
diff --git a/src/renderer/src/i18n/pt-BR/settings.json b/src/renderer/src/i18n/pt-BR/settings.json
index 4a133a74b..2861c13f9 100644
--- a/src/renderer/src/i18n/pt-BR/settings.json
+++ b/src/renderer/src/i18n/pt-BR/settings.json
@@ -658,8 +658,8 @@
     "stopModel": "Parar Modelo",
     "pulling": "Baixando...",
     "runModel": "Executar Modelo",
-    "voiceai": {
-      "title": "Texto para voz da Voice.ai",
+    "tts": {
+      "title": "Texto para fala (TTS)",
       "description": "Gere fala a partir de texto. As vozes aparecem na lista de modelos abaixo.",
       "audioFormat": {
         "label": "Formato de áudio",
diff --git a/src/renderer/src/i18n/ru-RU/settings.json b/src/renderer/src/i18n/ru-RU/settings.json
index e39cee514..48bc75332 100644
--- a/src/renderer/src/i18n/ru-RU/settings.json
+++ b/src/renderer/src/i18n/ru-RU/settings.json
@@ -652,8 +652,8 @@
     "stopModel": "Остановить модель",
     "pulling": "Скачивание...",
     "runModel": "Запустить модель",
-    "voiceai": {
-      "title": "Синтез речи Voice.ai",
+    "tts": {
+      "title": "Текст в речь (TTS)",
       "description": "Генерируйте речь из текста. Голоса отображаются в списке моделей ниже.",
       "audioFormat": {
         "label": "Аудиоформат",
diff --git a/src/renderer/src/i18n/zh-CN/settings.json b/src/renderer/src/i18n/zh-CN/settings.json
index dd405491d..5018eef0b 100644
--- a/src/renderer/src/i18n/zh-CN/settings.json
+++ b/src/renderer/src/i18n/zh-CN/settings.json
@@ -794,8 +794,8 @@
         "operationalDescription": "同步 ModelScope 平台上可直接使用的 MCP 服务器"
       }
     },
-    "voiceai": {
-      "title": "Voice.ai 文字转语音",
+    "tts": {
+      "title": "文本转语音 (TTS)",
       "description": "将文本生成语音，voice 会在下方模型列表中展示。",
       "audioFormat": {
         "label": "音频格式",
diff --git a/src/renderer/src/i18n/zh-HK/settings.json b/src/renderer/src/i18n/zh-HK/settings.json
index f3a97f6e3..cd6f0a35a 100644
--- a/src/renderer/src/i18n/zh-HK/settings.json
+++ b/src/renderer/src/i18n/zh-HK/settings.json
@@ -653,8 +653,8 @@
     "stopModel": "停止模型",
     "pulling": "拉取中...",
     "runModel": "運行模型",
-    "voiceai": {
-      "title": "Voice.ai 文字轉語音",
+    "tts": {
+      "title": "文字轉語音 (TTS)",
       "description": "將文字生成語音，voice 會在下方模型列表中顯示。",
       "audioFormat": {
         "label": "音訊格式",
diff --git a/src/renderer/src/i18n/zh-TW/settings.json b/src/renderer/src/i18n/zh-TW/settings.json
index 1233fae96..f9e6ce075 100644
--- a/src/renderer/src/i18n/zh-TW/settings.json
+++ b/src/renderer/src/i18n/zh-TW/settings.json
@@ -658,8 +658,8 @@
     "stopModel": "停止模型",
     "pulling": "下載中...",
     "runModel": "執行模型",
-    "voiceai": {
-      "title": "Voice.ai 文字轉語音",
+    "tts": {
+      "title": "文字轉語音 (TTS)",
       "description": "將文字生成語音，voice 會在下方模型清單中顯示。",
       "audioFormat": {
         "label": "音訊格式",