AI 导读
Google DeepMind 发布 Gemini 3.8 Flash TTS 与 Gemini 3.8 Flash-Lite TTS 两款文本转语音模型，前者可设计带不同口音和特征的音色，后者面向效率与规模化，可选用自建风格或官方音色库。作者 @fofrAI 用一段描述 1930 年代中大西洋新闻片解说员的提示词演示了音色设计，并附上演示链接。
正文
Voice design is fun:
> A 1930s Mid-Atlantic newsreel commentator. Brassy, forward-placed theatrical tenor with crisp trilled r's, punchy staccato phrasing, and vintage ribbon-microphone midrange projection. https://t.co/HlzuJyND3d https://t.co/ssqOYrivVE
Create and deploy custom audio with our new text-to-speech models: 🔵 Gemini 3.8 Flash TTS: Design unique voices with distinct accents and characteristics. 🔵 Gemini 3.8 Flash-Lite TTS: Built for efficiency and scale, choose from your created styles or our expansive production-ready library.在 X 查看被引用的帖子
来源：@fofrAI · x.com