谷歌 Gemini 3.5 Live Translate 发布：支持70多种语言的实时语音翻译
谷歌发布 Gemini 3.5 Live Translate 音频模型，为超过70种语言提供实时语音翻译。系统无需等待句子结束即可持续翻译，并宣称能保留说话者的语调、语速和音高。在 Google Meet 中，语言支持从5种扩展至70多种。
Google's Gemini 3.5 Live Translate delivers real-time voice translation across 70+ languages
Google releases Gemini 3.5 Live Translate, a real-time audio translation model for 70+ languages. The model detects languages automatically and, according to Google, preserves the speaker's tone, pace, and pitch. It also translates continuously without waiting for a sentence to end.
Gemini 3.5 Live Translate is available now for developers through the Gemini Live API and Google AI Studio, as a preview for businesses in Google Meet, and for all users in the Google Translate app on Android and iOS. In Google Meet, language support jumps from five to over 70 languages with more than 2,000 language combinations. Ride-hailing service Grab is reportedly testing the model for driver-passenger communication. All generated audio is tagged with an inaudible SynthID watermark.
AI News Without the Hype – Curated by Humans