Google releases Gemini 3.5 Live Translate, its latest audio model that it says can deliver “near real-time speech-to-speech translation in over 70 languages”
Gemini 3.5 Live Translate is our latest audio model, delivering near real-time speech-to-speech translation in over 70 languages.
The Keyword
Context & Ripple Effects
Google’s recent audio-model releases have moved along the real-time voice stack: Gemini 3.1 Flash Live emphasized lower-latency dialogue and tonal understanding, while Gemini 3.1 Flash TTS added multilingual speech generation and granular controls.
Live Translate extends that progression into speech-to-speech translation. It also follows Google Translate’s expansion of live speech translation beyond Pixel Buds to compatible Android phones and headphones.
First-order effects
Google adds a Gemini 3.5 audio model positioned for near-real-time, speech-to-speech translation across more than 70 languages.
The release gives Google a more explicit translation-focused component alongside its live-dialogue and text-to-speech models.
Second-order effects
Products built around live conversations can potentially combine Google’s dialogue, speech-generation, and translation capabilities rather than treating translation as a separate text-first step.
Google’s broader translation offerings face pressure to make multilingual voice interaction available across more device contexts, following the earlier move from Pixel Buds to any compatible headphones.
Third-order effects
If these releases continue to converge, real-time multilingual voice interaction could become a standard platform capability rather than a standalone translation feature.
The accompanying use of audio watermarking on Gemini 3.1 Flash Live suggests that provenance mechanisms may become more relevant as synthetic and translated speech are used in live interactions.
The trend: Google is assembling a multilingual, low-latency voice-AI stack in which conversation, speech generation, and translation increasingly operate as one real-time layer.
🚨 Google has just released Gemini 3.5 Live Translate, an audio model delivering near real-time speech-to-speech translation. This is incredible work from the Google DeepMind team. [video]
Fascinating. Google just released Gemini 3.5 Live Translate. A live speech-to-speech translation model that starts speaking in another language while the original speaker is still talking. Older translation systems often wait for a full sentence, because early words can be [video…
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural. It is available in the Gemini API, AI Studio, & Google Translate right now + coming soon to Google Meet!! [vid…
Rolls out today, including in the Google Translate app on Android and iOS -> Google releases Gemini 3.5 Live Translate, which it says can deliver “near real-time speech-to-speech translation in over 70 languages Will also work in Google Meet -> Speech translation in Google [image…
introducing gemini 3.5 live translate, our latest audio model: - low-latency translation across 70+ languages - auto-detection for multilingual inputs in a single session - native audio processing that preserves pitch & pacing - robust noise filtering for loud environments try [v…
Gemini 3.5 Live Translate! We just shipped a real-time babel fish. - 70+ languages, 2,000+ language pairs. - Natural translated speech, works in noisy environments. - Stays in sync with the speaker, no lag, no awkward pauses. - Auto-detects the language being spoken. Available [v…
do you understand what Google just did? they made the language barrier disappear in real time. 70+ languages. no pauses. it's called Gemini 3.5 Live Translate. and it just dropped for developers today. here's what makes it different: most translation tools wait for you to [video]
Gemini 3.5 Live Translate! We just shipped a real-time babel fish. — 70+ languages, 2,000+ language pairs. — Natural translated speech, works in noisy environments. …