隨著全球直播產業的快速成長，語言隔閡已成為跨國互動中的主要障礙。我負責「直播即時翻譯平台」的專案管理、系統架構設計、前端開發與網域部署。此平台為一套以網頁為基礎的系統，整合了語音辨識、AI 翻譯與字幕呈現等技術。

前端採用 HTML、CSS 與 JavaScript 開發，後端則以 Flask 搭配 stream-translator-gpt、chat-downloader 等開源工具，並結合大型語言模型（OpenAI、Gemini 以及本地端 Gemma）進行語音與文字翻譯。平台支援直播音訊與聊天室訊息的即時翻譯，並提供字幕匯出與介面主題自訂功能，為使用者帶來更優質的跨語言觀看體驗。此專案展現了 AI 輔助語言溝通在媒體、教育與數位應用領域中的高度潛力。

With the rapid growth of the global live streaming industry, language barriers have become a major obstacle to cross-border interaction. I led project management, system architecture design, front-end development, and domain deployment for the Live Streaming Real-Time Translation Platform, a web-based system that integrates speech recognition, AI translation, and subtitle rendering technologies.

The frontend is built with HTML, CSS, and JavaScript, while the backend uses Flask and open-source tools such as stream-translator-gpt and chat-downloader, leveraging large language models (OpenAI, Gemini, and local Gemma) for speech and text translation. The platform supports real-time translation of live audio and chat messages, along with subtitle export and customizable interface themes, providing an enhanced cross-lingual viewing experience. This project demonstrates the potential of AI-assisted language communication for media, education, and digital applications.