Gemini 3.8 TTS：多角色语音与低成本试验
中文全文 · AI 翻译
新的 Gemini 3.8 TTS 模型超级便宜，而且可以生成多个声音之间的对话（超过 2000 种，或者你可以克隆自己的声音）——我为它建了一个小 UI，然后让 Claude 快速写了个脚本，里面有两只鹈鹕辩论要不要搬到 Pacifica Pier https://simonwillison.net/2026/Sep/23/gemini-tts-playground/
Flash 的生成音频每分钟成本似乎不到 1 美分，而 Flash-Lite 甚至比这还要便宜。
对照原文
The new Gemini 3.8 TTS models are super-cheap and can generate conversations between multiple voices (from 2,000+, or you can clone your own) - I built a little UI for it, then had Claude knock up a script where two pelicans debate moving to Pacifica Pier https://t.co/7PFM1ASAOl
Seems to cost less than 1 cent per minute of generated audio for Flash, and Flash-Lite is even cheaper than that