88Z AI, 10 June — Google has released Gemini 3.5 Live Translate, supporting real-time translation for over 70 languages while preserving original tone and speed with only a few seconds of latency. Developers can access the API preview, enterprises can use it in Google Meet, and general users can try it via the Google Translate app.
At a glance
- Supports real-time translation for 70+ languages, preserving original tone and speed
- Available to developers, enterprises, and general users across multiple platforms
The update
Google has officially launched the real-time speech translation model, Gemini 3.5 Live Translate. This model automatically identifies over seventy languages and generates fluent translated speech that fully preserves the original speaker's tone, speed, and pitch. Technically, the model balances waiting for context with immediate output, ensuring the translation lags only a few seconds behind the original audio for a highly natural interactive experience. Currently, the model is accessible to various user groups through different channels. Developers can apply for the Gemini Live API preview and integration; enterprise users can directly apply this technology within Google Meet scenarios; and the general public can easily experience this real-time translation feature via the Google Translate app to communicate across language barriers.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- IT之家Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.