Google's real-time speech translation model that preserves the speaker's voice, intonation and pacing across 70+ languages.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Gemini 3.5 Live Translate is a real-time speech-to-speech translation model from Google. According to a creator summary, it keeps the original speaker's voice, intonation and pacing in the translated output, detects the spoken language automatically across more than 70 languages, and runs a few seconds behind the speaker.
It is reported to be available through the Gemini API, Google AI Studio and Google Translate, so it can be used by developers building live translation into their own applications as well as by end users in Google's consumer product. Details such as exact language lists, latency figures and model identifiers should be checked in the official documentation.
The information here comes mainly from a single secondary source; the official page fetched was the general Gemini landing page and did not describe this model. Pricing, release date and technical limits are not confirmed.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Real-time speech translation model that keeps the speaker's voice, intonation and pacing, detects 70+ languages, and stays a few seconds behind. Available via API, AI Studio and Google Translate.
Near real-time speech translation model, coming to Google Meet and Google Translate and available in AI Studio. Creator tested live translation to Hindi and Spanish from a YouTube tab.
Closest neighbours by meaning, not just by category.
Model · Google
Google's real-time voice model with an Extended Thinking variant, available in the Gemini app, AI Studio and Search Live.
Model · Google
Google's low-latency, bidirectional voice and audio streaming models, accessed through the Gemini Live API.
Model · Google
Google's speech-to-text model with verbatim and smart modes, speaker detection, word timestamps and a live streaming variant.
Model · Google
Google's Gemini 3.8 text-to-speech model for expressive, controllable speech generation via the Gemini API and AI Studio.
Model · Google
Google's text-to-speech models in the Gemini API for controllable, multi-speaker speech generation from text.
Model · Google
Google Gemini 3.8 Live feature pairing real-time video generation with speech for conversational face-to-face avatars.
