工具POST
Gemini TTS 支持逐行调节语气并加 SynthID 水印
新 TTS 模型可逐行调整节奏、情绪和笑声停顿等提示，所有生成音频都嵌入 SynthID 水印以便识别。
Google DeepMind
@GoogleDeepMind2026.09.24收录原推发布于 2026.09.23
Google DeepMind @GoogleDeepMind原推发布于 2026.09.23
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 → https://t.co/F93tMO9Fxt
x.com/googledeepmind/status/2102781533274734801采集于 2026.09.24 11:02