Gemini 3.5 Live Translate: Real-Time Speech-to-Speech Translation Launched on Google AI Studio, Translate & Meet
English summary
Google has released Gemini 3.5 Live Translate, an audio model designed specifically for near real-time speech-to-speech translation. The feature is now available within Google AI Studio, Google Translate, and Google Meet. It produces natural-sounding translated speech with low latency, aiming to enable seamless multilingual conversations in live meetings and direct translations without a text intermediary.
Chinese summary
谷歌发布了Gemini 3.5 Live Translate，这是一个专为近乎实时语音到语音翻译设计的音频模型。该功能现已集成至Google AI Studio、Google Translate和Google Meet中，能生成低延迟的自然翻译语音，目标是在实时会议和直接翻译中实现无缝多语言对话，不再依赖文字中转。
Key points
Gemini 3.5 Live Translate is a new audio model focused on live speech-to-speech translation.
Gemini 3.5 Live Translate是一个专注于实时语音到语音翻译的新音频模型。
The translation service is integrated into Google AI Studio, Google Translate, and Google Meet.
该翻译服务已集成到Google AI Studio、Google Translate和Google Meet中。
It delivers near real-time translations with natural speech output.
它提供了近乎实时的翻译和自然的语音输出。