- Gemini 3.5 Live Translate is our latest audio model, delivering near real-time speech-to-speech translation in over 70 languages.
- The model automatically detects 70+ languages and generates smooth, natural-sounding translated speech that preserves the speakers' intonation, pacing and pitch.
- It delivers fluid audio without awkward pauses and stays just a few seconds behind the speaker throughout the session.
- Gemini 3.5 Live Translate is rolling out starting today across Google products.
Google's Gemini 3.5 Live Translate is designed for near real-time speech-to-speech translation, offering fluid audio in over 70 languages. The system automatically detects languages and generates translated speech that maintains the original speaker's intonation, pacing, and pitch.12
The model minimizes awkward pauses, providing seamless conversations by staying just a few seconds behind the speaker. Launching today across Google products, it aims to enhance communication for over 10 million monthly voice calls executed through partners like Grab, which tests the model for interactions between drivers and travelers at pickup4
In addition to Grab, the technology will support organizations like CJ ENM, facilitating discussions across 2000+ language combinations in a single meeting, a significant improvement from earlier models that only translated to and from English. This evolution in translation technology highlights Google's commitment to bridging communication gaps across diverse linguistic backgrounds.
“Gemini 3.5 Live Translate introduces audio translation for over 70 languages, significantly improving multilingual communication capabilities. The model is now rolling out on Google products, offering real-time speech-to-speech translation.”
