Google DeepMind· @GoogleDeepMind · X·· 7 天前AI 评分54
AI 导读
Google DeepMind 宣布可在 Gemini API 中逐行微调语音生成，控制节奏、情绪以及笑声、停顿等提示。所有生成音频均带有 SynthID 水印，可被可靠识别为 AI 生成，开发者可通过 Google AI Studio 开始构建。
正文
Fine-tune the delivery line by line, shaping pacing, emotion, and cues like laughs or pauses.
All generated audio is watermarked with SynthID so it can be reliably identified as AI-generated.
Start building with the Gemini API via @GoogleAIStudio. Find out more →
来源：Google DeepMind · x.com