feat(tts): add Xiaomi MiMo text-to-speech support

Adds mimo-v2.5-tts as a Media Provider TTS through the existing
OpenAI-compatible chat-completions endpoint. Voice is selected via the
top-level audio.voice field, and an optional style/language hint is
threaded through tts.js -> ttsCore.js -> the new adapter.

public/i18n/literals/zh-TW.json

@@ -12,6 +12,7 @@
   "Logout": "登出",
   "Login": "登錄",
   "Providers": "提供者",
+  "Style": "風格",
   "Usage": "統計",
   "API Key": "API 金鑰",
   "Connected": "已連接",
@@ -176,6 +177,7 @@
   "How it works:": "工作原理：",
   "Antigravity/Copilot IDE request → DNS redirect to localhost:443 → MITM proxy intercepts → 9Router → response to Antigravity/Copilot": "Antigravity/Copilot IDE 請求 → DNS 重定向到 localhost:443 → MITM 代理攔截 → 9Router → 响應到 Antigravity/Copilot",
   "No API keys — create one in Keys page": "沒有 API 金鑰 — 在金鑰頁面中創建一個",
+  "e.g. a warm, gentle voice, speaking slowly with a British accent": "例如：溫暖柔和的嗓音，用英式口音緩慢說話",
   "sk_9router (default)": "sk_9router（默認）",
   "Server started": "服務器已啟動",
   "Failed to start server": "啟動服務器失敗",