Google's new AI model will translate over 70 languages ​​seamlessly, preserving tone and speed..

On Wednesday, Google launched its latest speech-to-speech translation model, named Gemini 3.5 Live Translate. Google claims it is designed to enable more natural conversations across different languages. According to the company, this new AI model can detect over 70 languages ​​and generate translated speech. It is claimed that the model preserves the speaker's tone, pacing, and intonation while delivering continuous, near-real-time translation. Gemini 3.5 Live Translate is being rolled out to Google Translate, Google Meet, Google AI Studio, and the Gemini Live API for developers.

Gemini 3.5 Live Translate processes audio via real-time streaming.
In a blog post, Google emphasized that Gemini 3.5 Live Translate represents the next major step in its translation efforts, which began nearly two decades ago with some of the company's earliest machine learning experiments. The company claims the model is ideal for multilingual meetings, live broadcasts, lessons, customer support interactions, and real-time interpretation.

According to Google, Gemini 3.5 Live Translate handles live translation with minimal latency. It processes audio as it streams in real-time, generating translated audio within just a few seconds of the original speaker's words. The company stated that this eliminates the pauses typically found in traditional turn-based translation systems.

Google says this new speech-to-speech translation model can identify and switch between more than 70 languages, removing the need to manually configure language settings. It is reported that Gemini 3.5 Live Translate remains highly effective even in noisy and unpredictable environments.

The company announced that this upgraded translation capability is also coming to the Google Meet app. Like Live Translate, this app will support translation across more than 70 languages—a significant leap from the previous limit of five languages. Additionally, the tech giant is bringing Gemini 3.5 Live Translate to the Google Translate app on both Android and iOS. It will be available via the Live Translate feature within the app, and translated speech can be heard through any paired, compatible headphones.

On Android, Google is rolling out a 'Listening Mode' that allows translated audio to play directly through the smartphone's earpiece.

Addressing concerns regarding AI-generated content, the company noted that all audio generated by Gemini 3.5 Live Translate will embed its 'SynthID' watermarking technology. This technology is integrated directly into the generated audio and is designed to help identify AI-generated content.

Developers can access Gemini 3.5 Live Translate in public preview via the 'Gemini Live API' and 'Google AI Studio.' Google has highlighted integrations with platforms such as Agora, Fishjam, LiveKit, Pipecat, and Vision Agents to help developers build and deploy voice translation applications more easily. This AI model is rolling out globally across supported Google products starting today.

Disclaimer: This content has been sourced and edited from Dainik Jagran. While we have made modifications for clarity and presentation, the original content belongs to its respective authors and website. We do not claim ownership of the content.