Gemini 3.8 TTS 试玩场：两款新语音模型与自定义声音
原标题：Gemini 3.8 TTS Playground
AI 摘要
Google 发布了两款新的 Gemini 文本转语音模型 gemini-3.8-flash-tts 和 gemini-3.8-flash-lite-tts，提供超过 2000 种声音库，并支持仅用 30 秒音频样本创建自定义声音。Simon Willison 用 GPT-6 Astra 快速搭建了一个自带密钥的试玩界面，利用 Gemini API 的开放 CORS 策略。该 API 便于定义多角色对话，每个角色可配置不同声音和风格指令。
正文节选
23rd September 2026 Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use". I vibe coded this bring-your-own-key playground interface with GPT-6 Astra, taking advantage of the open CORS policy of the underlying Gemini API. A notable feature of the API is that it m