产品多源确认

Google 开放 Gemini API 逐行微调语音合成,含 SynthID 水印

Fine-tune the delivery line by line, shaping pacing, emotion, and cues like laughs or pauses. All ...

精选理由

Google 在 Gemini API 里开放了逐行调语气的语音生成,能控制节奏、情绪甚至笑声停顿,还自带 SynthID 水印,做语音产品的可以去 AI Studio 试试。

Google DeepMind 宣布开发者可通过 Gemini API 使用语音生成功能。用户能逐行微调台词的节奏、情绪,并加入笑声、停顿等提示。所有生成音频均带 SynthID 水印,可被识别为 AI 生成内容。开发可在 Google AI Studio 中上手。

图片来源 · Google DeepMind
原文 · Google DeepMind

Fine-tune the delivery line by line, shaping pacing, emotion, and cues like laughs or pauses. All ...

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 → goo.gle/4dw40ns 💬 10 🔄 2 ❤️ 31 👀 4358 📊 11 ⚡