Google Gemini 3.5 Live Translate: Real-Time Voice Translation Breaks the Language Barrier

Imagine talking with a foreign partner with no interpreter, no waiting, no typing. That is what Google just launched.

What Is Live Translate?

Google announced Gemini 3.5 Live Translate on June 9, 2026, a real time speech-to-speech translation feature supporting more than 70 languages, including Vietnamese.

The biggest difference from anything that came before is that it does not wait for you to finish a sentence before translating. Speech is processed and converted continuously, following the flow of the conversation, with almost no delay.

The Technology Behind It

Most traditional translation systems work in a pipeline: listen, convert to text, translate the text, read it back. Each step takes time and creates a natural break in the conversation.

Gemini 3.5 Live Translate breaks that pattern by translating directly from speech to speech, with no text step in between. This is the result of Gemini 3.5's multimodal architecture, which processes text, image, video, and audio simultaneously within the same model.

The continuous streaming technique (no sentence level delays) makes the translated voice sound more natural, without being cut off clause by clause.

Where Can You Use It?

Real world situations where this can be applied right away include:

International conferences with multiple languages involved, where hiring interpreters is expensive. Cross language interviews for journalism, recruiting, or user research. Tourists communicating with locals without needing a text input app. And more importantly, it can replace interpreters in a wide range of everyday situations.

Available Today

The feature is already available through Google AI Studio, no waiting required. If you are building a product with a multilingual angle, now is the time to test it directly.

Comparing With Older Systems

Traditional systems: listen to the full sentence, translate it, read it back, with a delay of 2 to 4 seconds per sentence, breaking up the conversation.

Gemini 3.5 Live Translate: translates with continuous streaming, no text step in between, voice that sounds more natural, an experience close to a real conversation.

In real conversations, a few seconds of waiting can completely break the feeling of connection. That is why this step forward matters more than the technical numbers suggest.

How do you think this feature will change the way you work with foreign partners?