diff --git a/app/src/components/ServerTab/GenerationPage.tsx b/app/src/components/ServerTab/GenerationPage.tsx
index 2b868593..b195df73 100644
--- a/app/src/components/ServerTab/GenerationPage.tsx
+++ b/app/src/components/ServerTab/GenerationPage.tsx
@@ -140,43 +140,38 @@ export function GenerationPage() {
 
       <aside className="hidden lg:block w-[280px] shrink-0 space-y-6 sticky top-0">
         <div className="space-y-2">
-          <h3 className="text-sm font-semibold">About voice generation</h3>
+          <h3 className="text-sm font-semibold">{t('settings.generation.sidebar.aboutTitle')}</h3>
           <p className="text-sm text-muted-foreground leading-relaxed">
-            Clone a voice from a short sample, then generate speech in any voice
-            across any language. Ship TTS into AI agents, games, podcasts, or
-            long-form narration.
+            {t('settings.generation.sidebar.aboutBody')}
           </p>
         </div>
 
         <div className="space-y-3">
-          <h3 className="text-sm font-semibold">What's different</h3>
+          <h3 className="text-sm font-semibold">{t('settings.generation.sidebar.differencesTitle')}</h3>
           <ul className="space-y-3 text-sm text-muted-foreground">
             <li className="flex gap-2.5">
               <Mic className="h-4 w-4 shrink-0 mt-0.5 text-accent" />
               <span className="leading-relaxed">
                 <span className="text-foreground font-medium">
-                  Clone any voice in seconds.
+                  {t('settings.generation.sidebar.clone.title')}
                 </span>{' '}
-                A few seconds of reference audio is enough. Multi-sample support
-                for higher quality when you want it.
+                {t('settings.generation.sidebar.clone.body')}
               </span>
             </li>
             <li className="flex gap-2.5">
               <Languages className="h-4 w-4 shrink-0 mt-0.5 text-accent" />
               <span className="leading-relaxed">
                 <span className="text-foreground font-medium">
-                  Seven engines, 23 languages.
+                  {t('settings.generation.sidebar.engines.title')}
                 </span>{' '}
-                Pick the tradeoff that fits — quality, speed, or multilingual
-                coverage.
+                {t('settings.generation.sidebar.engines.body')}
               </span>
             </li>
             <li className="flex gap-2.5">
               <Zap className="h-4 w-4 shrink-0 mt-0.5 text-accent" />
               <span className="leading-relaxed">
-                <span className="text-foreground font-medium">Agent-ready.</span>{' '}
-                REST API with per-profile control — give any AI a voice you've
-                cloned.
+                <span className="text-foreground font-medium">{t('settings.generation.sidebar.agentReady.title')}</span>{' '}
+                {t('settings.generation.sidebar.agentReady.body')}
               </span>
             </li>
           </ul>
diff --git a/app/src/i18n/locales/en/translation.json b/app/src/i18n/locales/en/translation.json
index 00d5493f..91fdd00c 100644
--- a/app/src/i18n/locales/en/translation.json
+++ b/app/src/i18n/locales/en/translation.json
@@ -826,6 +826,23 @@
         "title": "Generations folder",
         "description": "Where generated audio files are stored on disk.",
         "open": "Open"
+      },
+      "sidebar": {
+        "aboutTitle": "About voice generation",
+        "aboutBody": "Clone a voice from a short sample, then generate speech in any voice across any language. Ship TTS into AI agents, games, podcasts, or long-form narration.",
+        "differencesTitle": "What's different",
+        "clone": {
+          "title": "Clone any voice in seconds.",
+          "body": "A few seconds of reference audio is enough. Multi-sample support for higher quality when you want it."
+        },
+        "engines": {
+          "title": "Seven engines, 23 languages.",
+          "body": "Pick the tradeoff that fits — quality, speed, or multilingual coverage."
+        },
+        "agentReady": {
+          "title": "Agent-ready.",
+          "body": "REST API with per-profile control — give any AI a voice you've cloned."
+        }
       }
     },
     "captures": {
diff --git a/app/src/i18n/locales/ja/translation.json b/app/src/i18n/locales/ja/translation.json
index 0c90da56..7508aa2e 100644
--- a/app/src/i18n/locales/ja/translation.json
+++ b/app/src/i18n/locales/ja/translation.json
@@ -826,6 +826,23 @@
         "title": "生成物の保存先フォルダ",
         "description": "生成されたオーディオファイルをディスク上に保存する場所。",
         "open": "開く"
+      },
+      "sidebar": {
+        "aboutTitle": "音声生成について",
+        "aboutBody": "短いサンプルからボイスをクローンし、あらゆる言語のあらゆるボイスで音声を生成できます。TTS を AI エージェント、ゲーム、ポッドキャスト、長尺ナレーションに組み込めます。",
+        "differencesTitle": "ここが違います",
+        "clone": {
+          "title": "数秒でどのボイスでもクローン。",
+          "body": "数秒のリファレンス音声があれば十分です。より高い品質を求めるときは複数サンプルにも対応します。"
+        },
+        "engines": {
+          "title": "7 つのエンジン、23 言語。",
+          "body": "品質、速度、多言語対応 — 用途に合ったトレードオフを選べます。"
+        },
+        "agentReady": {
+          "title": "エージェント対応。",
+          "body": "プロファイル単位で制御できる REST API — クローンしたボイスをどの AI にも渡せます。"
+        }
       }
     },
     "captures": {
diff --git a/app/src/i18n/locales/zh-CN/translation.json b/app/src/i18n/locales/zh-CN/translation.json
index 19b990d3..66d91bcb 100644
--- a/app/src/i18n/locales/zh-CN/translation.json
+++ b/app/src/i18n/locales/zh-CN/translation.json
@@ -826,6 +826,23 @@
         "title": "生成文件夹",
         "description": "生成的音频文件在磁盘上的存储位置。",
         "open": "打开"
+      },
+      "sidebar": {
+        "aboutTitle": "关于语音生成",
+        "aboutBody": "用一段简短样本克隆声音,然后用任意声音、任意语言生成语音。把 TTS 接入 AI 代理、游戏、播客或长篇旁白。",
+        "differencesTitle": "不同之处",
+        "clone": {
+          "title": "几秒内克隆任意声音。",
+          "body": "几秒钟的参考音频就足够了。需要更高质量时,支持多样本克隆。"
+        },
+        "engines": {
+          "title": "七种引擎,23 种语言。",
+          "body": "选择最合适的取舍——质量、速度,或多语言覆盖。"
+        },
+        "agentReady": {
+          "title": "面向代理。",
+          "body": "REST API 支持按档案控制——给任何 AI 一个您克隆的声音。"
+        }
       }
     },
     "captures": {
diff --git a/app/src/i18n/locales/zh-TW/translation.json b/app/src/i18n/locales/zh-TW/translation.json
index 5c66ecf5..7ed5c22c 100644
--- a/app/src/i18n/locales/zh-TW/translation.json
+++ b/app/src/i18n/locales/zh-TW/translation.json
@@ -826,6 +826,23 @@
         "title": "生成資料夾",
         "description": "生成的音訊檔案在磁碟上的儲存位置。",
         "open": "開啟"
+      },
+      "sidebar": {
+        "aboutTitle": "關於語音生成",
+        "aboutBody": "從一段簡短的樣本複製聲音,然後以任何聲音、跨任何語言生成語音。將 TTS 送進 AI 代理、遊戲、Podcast 或長篇旁白。",
+        "differencesTitle": "有何不同",
+        "clone": {
+          "title": "幾秒內複製任何聲音。",
+          "body": "幾秒鐘的參考音訊就夠了。需要更高品質時也支援多樣本。"
+        },
+        "engines": {
+          "title": "七種引擎、23 種語言。",
+          "body": "選擇最符合需求的取捨——品質、速度,或多語言覆蓋。"
+        },
+        "agentReady": {
+          "title": "代理就緒。",
+          "body": "REST API 提供逐一聲音檔案的控制——讓任何 AI 擁有您複製過的聲音。"
+        }
       }
     },
     "captures": {