Philipp Schmid· @_philschmid · X·· 11 天前精选AI 评分69
AI 导读
Philipp Schmid 介绍 Gemini 3.8 TTS 支持通过录制 20 秒语音加同意句复刻个人声音，或用提示词设计完全自定义的语音。通过 API 调用创建后可在任意请求中使用，风格通过 speech_metadata 设置，作者还提供了博客链接和一段可交给智能体的完整操作提示词。
推荐理由
原文给出录制片段、API 创建与调用的具体步骤和可复用提示词，方便读者快速试用自己的语音复刻。
正文 · 原文
With Gemini 3.8 TTS you can replicate your voice or design a completely custom one from a prompt
- Record 20s of you talking + the consent sentence
- Create your Voice via API call
- Use it in any request, style goes in speech_metadata
Past this into your agent
"Read https://www.philschmid.de/gemini-3-8-tts and walk me through creating my own voice for Gemini 3.8 TTS. Check my setup first (GEMINI_API_KEY, ffmpeg, gemini-skills), help me record the two clips, create the voice, and generate a test line I can listen to."
or read below.
https://x.com/i/article/2103140786292269056在 X 查看被引用的帖子
来源：Philipp Schmid · x.com