Google has announced Gemini 3.5 Live Translate, a new audio model designed to make multilingual conversations more natural by translating speech in real time. The company says the technology removes the delays associated with conventional voice translation tools and supports more than 70 languages.

The latest addition aims to enable smoother conversations by processing speech continuously rather than waiting for users to complete an entire sentence before generating a response.

Real-Time Translation Without Interruptions

Unlike traditional turn-by-turn translation systems, Gemini 3.5 Live Translate begins processing speech as soon as a person starts speaking and generates translated audio continuously. According to Google, the model is designed to strike a balance between gathering enough context for accuracy and maintaining synchronisation with the speaker.

The company said the technology eliminates awkward pauses and choppy audio, making conversations feel more natural and helping bridge language barriers.

Apple also offers a Live Translation feature, but support is currently limited to a smaller number of languages. Google’s new model expands coverage to more than 70 languages and is designed to preserve a speaker’s intonation, pacing and delivery, resulting in more natural-sounding translated speech.

Google added that all audio generated by its models is protected with SynthID watermarking. The watermark is embedded directly into the audio output and is designed to be imperceptible to users while remaining detectable when required.

Listening Mode Comes to Translate

Google has also introduced a new Listening Mode for situations where users do not have headphones available. Once enabled, users can place their phone near their ear, similar to a regular phone call, and listen to translated audio through the device’s earpiece.

The company is bringing the feature to the Google Translate app as well, allowing users to access translated speech more conveniently.

The announcement is part of Google’s broader efforts to improve accessibility and enhance communication tools powered by artificial intelligence. The company revealed that more than a trillion words are translated every month across its products for billions of users worldwide.

Google Meet Gets Expanded Language Support

Google is extending Gemini 3.5 Live Translate to Google Meet, significantly expanding the platform’s speech translation capabilities. Previously, Meet offered support for five languages. With the latest update, the service will support over 70 languages in real time.

According to Google, this will enable more than 2,000 language combinations within a single meeting, removing the previous limitation of translating only to and from English. The Meet interface is also being updated to provide faster access to speech translation features.

Gemini 3.5 Live Translate has already started rolling out to Google Translate on Android and iOS devices. For developers, the model is available in public preview through the Gemini Live API and Google AI Studio.

Meanwhile, the Google Meet integration will enter private preview for select Workspace users later this month.

Google said its latest translation advancements are aimed at making communication more seamless and helping users interact naturally, regardless of the language they speak.

Long or Short, get news the way you like. No ads. No redirections. Download Newspin and Stay Alert, The CSR Journal Mobile app, for fast, crisp, clean updates!

App Store –  https://apps.apple.com/in/app/newspin/id6746449540 

Google Play Store – https://play.google.com/store/apps/details?id=com.inventifweb.newspin&pcampaignid=web_share