Google releases Gemini 3.5 Live Translate, it can translate over 70 languages in real-time

Google has released Gemini 3.5 Live Translate for real-time speech-to-speech translation in more than 70 languages. The new audio model is aimed at making it easier to have conversations in different languages without having to wait for the translation to happen.

In Short

• Google releases Gemini 3.5 Live Translate
• The company says this model can translate what you say in real-time
• The model can translate audio in over 70 languages

If you have used voice translation tools, you would likely have faced one issue – speed. You would need to wait for the translation to happen every time you spoke a sentence, something that may lead to awkward silences. But Google wants to fix this with its latest audio model, Gemini 3.5 Live Translate.

Google says that Gemini 3.5 Live Translate is built to translate conversations as they happen. And according to the company, it can do so in over 70 languages. Here are all the details.

What is Gemini 3.5 Live Translate?

Gemini 3.5 Live Translate differs from turn-by-turn systems that wait for a speaker to finish before responding. Instead, the model can process speech as soon as you start speaking and then generate translated audio continuously.

As per Google, the model can balance the need to wait for enough context to improve quality with the need to remain in sync with your speech. Google added, “No awkward pauses or choppy audio, just real connection without language barriers.”

Do note that Apple does have something similar with its Live Translation feature, but it is limited to only a handful of languages.

And Gemini 3.5 Live Translate is designed to preserve your intonation, pacing and speech. That is, the model is aimed at delivering more natural sounding audio than a robotic tone.

Google states that all audio generated by its models is watermarked with SynthID. The company claims that the watermark is imperceptible and embedded directly into the audio output so it can be detected easily.

New Listening Mode, real-time translation for Google Meet

Another addition is Listening Mode. If you need to translate audio, but do not have your headphones, you can now listen to it via your phone’s earpiece. You just need to turn on this mode, and put your phone near your ear, as you would do on a normal phone call.

And Google is bringing Gemini 3.5 Live Translate to Google Meet. While the platform did have speech translation support for five languages previously, it will now support over 70 languages, that too, in real-time.

This, the company says, will allow for more than 2,000 language combinations in a single meeting, instead of only translating to and from English. The Meet interface will also be updated to provide instant access to speech translation.

Google Gemini 3.5 Live Translate availability

As per the company, Gemini 3.5 Live Translate has begun rolling out on Google Translate on Android and iOS. For developers, the model is in public preview through the Gemini Live API and Google AI Studio. While the feature will be available on Google Meet in private preview for select Workspace users from this month.

Google says that more than a trillion words are now translated for billions of users across its products every month.

- Ends