产品 社区共识
Vidu 在英语中的标准读法是 「vee doo」(/ˈviːduː/)。
Vidu is the text-to-video AI model from Beijing Shengshu Technology and Tsinghua University (launched April 2024; Vidu Q1 shipped 2025). Stress falls on the FIRST syllable: VEE-doo. Shengshu chief scientist Zhu Jun explained at the 2024 Zhongguancun Forum that the name evokes "video" and the phrase "we do." Common mistake: non-native devs read it as VY-doo (long-i, as in "vie") or VID-oo (short-i, as in "video"); the correct branded vowel is a long /iː/, which is non-obvious because English "video" actually starts with a short-i /vɪd/.
来源:GDToday — Tsinghua/Shengshu unveil Vidu (name evokes "Video" and "We do")
读对项目名只是工程师文化的一部分 — 但开会时被人轻轻纠正、或者在 podcast 上被嘉宾礼貌打断的滋味,并不好受。Pronounce 是一个开源的开发者词汇发音词典,每条都标注来源、信心等级,并且有预渲染的音频可以直接听。
安装 CLI:git clone https://github.com/anzy-renlab-ai/pronounce.git && cd pronounce && ./install.sh