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-CN.json

@@ -1119,6 +1119,7 @@
   "Stop Server": "停止服务器",
   "Stopped": "已停止",
   "Strict Proxy": "严格代理",
+  "Style": "风格",
   "Subagent Model": "子代理模型",
   "Sudo Password Required": "需要 sudo 密码",
   "Sudo password is required": "需要 sudo 密码",
@@ -1312,6 +1313,7 @@
   "disabled": "已禁用",
   "dollars per million tokens": "美元 / 百万 Token",
   "e.g. CwhRBWXzGAHq8TQ4Fs17": "例如 CwhRBWXzGAHq8TQ4Fs17",
+  "e.g. a warm, gentle voice, speaking slowly with a British accent": "例如：温暖柔和的嗓音，用英式口音缓慢说话",
   "e.g. claude-opus-4-5": "例如 claude-opus-4-5",
   "e.g. my-model-id": "例如 my-model-id",
   "e.g. tts-1-hd": "例如 tts-1-hd",