Google Translate now updated with improved AI-based offline translation


Translation apps can really turn saviours, especially when you are travelling and you are surrounded by a language you can not speak or read. However, these apps can really fall short in places when you have poor internet connectivity. Fortunately, Google has fixed that.


This basically means that the technology will now run in the Google Translate apps directly on your Android or iOS device, so that you can get translations even when you don’t have access to an internet connection.

In the latest update, the company has announced that it is improving the Google Translate app, particularly for offline use. Google is now incorporating previously online-only neural machine translation (NMT) technology to its offline version.

Users will begin to see the change in the next week with support for 50 languages.

So far Google Translate app only lets you download dictionaries of various languages which can just translate words or small phrases if you are offline. But with the NMT technology getting offline, you can even get translations for an entire paragraphs, rather than piece by piece.

“It uses broader context to help determine the most relevant translation, which it then rearranges and adjusts to sound more like a real person speaking with proper grammar. This makes translated paragraphs and articles a lot smoother and easier to read,” Google wrote in its blog.

In order to try the offline translations, go to your Translate app on Android or iOS. If you have used offline translations before, you will notice a banner on your home screen that will lead you to update your offline files. If not, go to your offline translation settings and tap the arrow next to the language name to download the package for that language.


Each of these packages weigh between 35 to 45 MB. Once you have the file, you are ready to translate text regardless of an internet connection.


You may also like...

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: