Fluid, natural voice translation with Gemini 3.5 Live Translate
Gemini
Gemini 3.5 Live Translate is a new real-time, speech-to-speech AI model supporting over 70 languages with natural intonation and low latency.Summary
Google has introduced Gemini 3.5 Live Translate, an advanced audio model that provides near real-time, continuous speech-to-speech translation across more than 70 languages. By processing speech as it is streamed, the model maintains natural pacing and intonation without the awkward pauses typical of turn-based systems. The technology is being integrated into Google Meet, the Google Translate app for Android and iOS, and is available to developers via the Gemini Live API. Additionally, all audio generated by the model includes a SynthID watermark to ensure transparency and prevent misinformation.
(Source：Gemini)