Google plans to add a real-time translation feature to its Android version of Google Translate at some point in the future,media reported. This feature will allow the user to record audio in one language and render it in another language in real time. While the feature is still in the prototype stage, Google demonstrated the technology in a series of artificial intelligence demonstrations at its San Francisco office on Tuesday.
Google says the feature may need to be connected to the Internet at the time it is released, meaning it will be different from the current translation feature based on artificial intelligence and devices in Google Translate. The company says this is because real-time multilingual transcription is much more complex than simply translating written text from one language to another or entering a single voice sentence and translating it into another.
At least initially, it won’t support audio files, and it must be recorded in real time via a smartphone microphone, but Google says users can play and record recorded audio through speakers.
Google says that because audio is constantly being performed, its transcription capabilities constantly evaluate the entire sentence. In addition, it adds punctuation and corrects the selection of certain words based on the context of the sentence, as well as attempts to correct accents and local dialects.
Unfortunately, the company did not give a specific timetable for when Google would launch the real-time transcription function, but said it would launch it at some point in the future.