GEMINI 3.5 LIVE TRANSLATE

Fluid, natural voice translation powered by Google DeepMind

A New Era of Live Translation

Gemini 3.5 Live Translate is the latest audio model for live speech-to-speech translation. It processes speech continuously as it's streamed, balancing the trade-off between waiting for context to improve quality and translating immediately to stay in sync with the speaker. It automatically detects multiple languages and handles multilingual inputs, avoiding awkward pauses.

Live API
Public Preview
Multilingual
Seamless Processing
Robust
Noise Handling
AI Studio
Developer Access

Key Capabilities

Continuous Streaming

Processes speech continuously, allowing for fluid translation without waiting for the speaker to finish.

Noise Robustness

Ensures applications can handle loud and unpredictable environments, retaining high translation fidelity.

Multilingual Input

Handles inputs across various languages without the need to manually configure settings.

Building with 3.5 Live Translate

The Gemini Live API allows developers to build and deploy voice translation apps with ease. By handling complex real-time media streaming, platforms can focus on enhancing user experience for multilingual calls, meetings, lessons, and broadcasts.

Available in public preview via Gemini Live API and Google AI Studio