谷歌推出了新的文字转化语音模式, Google launches new text-to-speech model with 70+ languages and audio tags.

谷歌推出了双子座3.1 Flash TTS, 这是一个新的文字转换语音模型, Google has launched the Gemini 3.1 Flash TTS, a new text-to-speech model offering improved expressiveness and developer control. 该系统支持70多种语言,具有音频标签用于声风调整,并包括SynthID水印来检测人工智能生成的内容. The system supports over 70 languages, features audio tags for vocal style adjustments, and includes SynthID watermarks to detect AI-generated content. 它可以通过双子API和Google AI Studio获得. It is available via the Gemini API and Google AI Studio.