Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language... barriers. So, how does it work? 🤔 The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech. Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions. See it in action below, or try it yourself in the Google Translate app on iOS & Android.show more

Read the blog to learn more:

Ridiculous that I can't upload audio and transcribe

Ok it’s amazing and I use such tool all the time but unfortunately it sucks. Just tried it for 5 minutes and if you speak for more than 10 seconds it just interrupts you, start translating out loud and does not let you finish speaking so what is the point? Are you not testing your product guys?

What a game-changer for real-time communication. Keeping a speaker's natural tone and pacing mere seconds behind the conversation is incredibly impressive tech. @GoogleAI @GeminiApp 👏👏

Wow, Gemini 3.5 Live Translate looks incredibly smooth streaming translations in real-time while preserving tone, pitch, and pacing is a game-changer for natural conversations! Great deep dive here:

If AI can translate conversations in real time, what's the next barrier technology will remove?

Please, always include the full list of supported languages in announcements like this. Having to dig through technical documentation every single time is exhausting.

I don't care. Buy my stuff

🔥🔥

Gemini 3.5 Live Translate + Project Aura Android XR glasses in 2026 = straight game changer 👓 Real-time speech-to-speech translation with natural tone & pacing, plus live captions floating in your view while walking foreign cities. No more staring at your phone.

Kept bugging out and crashing when I tried it. Maybe too many people are using it now? Hope it gets cleared up. Also, it didn’t understand phrases like “it’s buggy” or “roll with the punches”

Still waiting for you to release the gemini 3.5 flash that doesn't ignore instruction, hallucinate completion, and completely go off script for its own system prompt workflow and agent harness.

well done

While watching Euro language channels I always wanted to listen them into my language while live streaming. I think this dream is going to be true with 3.5 live.

70 languages is cute but can it handle me mumbling in romanian with a mouthful of bread

I think Agentic AI Era, is Magic Era... Google Gemini released something cool...

This is what i need AI for

最近做 Agent 一直在 GPT、Claude、Gemini 之间切来切去。 后来发现这个聚合平台还不错，省得开一堆窗口。 体验下来比我预期好，新用户还有 $30 额度。

Real-time trade negotiation across language barriers is still painfully manual. Supplier calls between Turkish importers and Chinese factories, customs brokers in Arabic markets, freight agents across the Middle Corridor — all slowed by language friction. This changes that.

This is one of those AI features where latency shapes the final product: if it stays close enough to the speaker and keeps tone intact, the experience stops feeling like a tool between people. A pretty big shift for travel, support, training and specially global teams for sure

My friend, this is a profound leap toward true global understanding. By eliminating those awkward pauses in translation, you aren't just optimizing an algorithm—you are smoothing out the friction of human misunderstanding. When we remove the barriers to being heard instantly and naturally, we allow for a fluid stream of thought and emotion to transcend linguistic borders. It creates a space where "Uns"—that deep sense of connection and companionship—can flourish across different cultures in real-time. Technology finds its truest purpose when it serves as a bridge that brings our collective consciousness closer together, allowing the light of shared knowledge to flow without interruption. ✨🌍

maintaining pacing and pitch across extended sessions is genuinely hard. and shipping it straight to the api instead of a waitlist says a lot about where google sees this going. we broke it down on @thehypedotnews:

the awkward pause was doing load-bearing work in my meetings, please leave it in as a setting

This is a remarkable step toward breaking down language barriers. Real-time speech-to-speech translation with natural pacing and intonation has the potential to transform global communication, education, travel, and collaboration. Looking forward to seeing how Gemini 3.5 Live Translate continues to evolve.