What is Gemini 3.5 Live Translate?

Gemini 3.5 Live Translate is Google's latest audio model for near real-time speech-to-speech translation. It automatically detects over 70 languages and generates smooth, natural-sounding translated speech that preserves the speaker's original intonation, pacing, and pitch. Unlike older turn-by-turn systems that wait for a speaker to finish before responding, this model generates speech continuously—staying just a few seconds behind the speaker throughout the session.

Who it's for

• Developers building multilingual voice apps can integrate the model via the Gemini Live API and Google AI Studio.
• Enterprise teams needing live interpretation for meetings can access a private preview in Google Meet starting this month.
• Everyday travelers and multilingual communicators can use the feature directly in the Google Translate app on Android or iOS with any pair of headphones.

Key features

Continuous streaming translation

The model processes speech as it's streamed, balancing the trade-off between waiting for context to improve quality and translating immediately to stay in sync. This delivers fluid audio without awkward pauses.

Automatic language detection

Gemini 3.5 Live Translate handles multilingual inputs without requiring manual configuration. It automatically identifies the source language from over 70 options and generates the appropriate translation.

Noise robustness

The model is designed to handle loud, unpredictable environments, making it suitable for real-world applications like multilingual calls, meetings, lessons, and broadcasts.

Broad platform availability

The model rolls out across Google products: for developers via the Gemini Live API and Google AI Studio, for enterprises in Google Meet, and for consumers in the Google Translate app on both Android and iOS.

What stands out

"It delivers fluid audio without awkward pauses and stays just a few seconds behind the speaker throughout the session."

This continuous streaming approach is a fundamental shift from traditional translation systems. Instead of waiting for a complete sentence before responding, Gemini 3.5 Live Translate generates speech in near real-time, preserving the natural flow of conversation. The model also maintains the speaker's original tone and pacing, making interactions feel more human and less robotic.

Worth checking out if…

You need live, natural-sounding speech translation for multilingual meetings, customer support, travel, or any scenario where seamless cross-language communication matters. Developers building voice apps will find the Gemini Live API and partner integrations with platforms like Agora, LiveKit, and Pipecat especially useful for rapid deployment.