模型与实验室 3.0 · 值得看 2026-05-01 · 文章

Gemini 3.1 Flash TTS:最强表现力语音合成模型,70语言覆盖

质量评分:5 来源: com/GoogleAI/status/2044447638511383024 抓取时间: 2026-04-18 --- 原文: > Today we launched Gemini 3. 1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch includes audio tags. 🗣🏷 Audio

回到归档

质量评分:5 来源: com/GoogleAI/status/2044447638511383024 抓取时间: 2026-04-18 --- 原文: > Today we launched Gemini 3. 1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch includes audio tags. 🗣🏷 Audio