Google is continuing with its effort to become the one-stop translation shop, announcing today that it has added speech capabilities to more languages on Google Translate, its polylingual text translation tool.
The feature uses the open-source speech synthesizer eSpeak to turn text into sound, giving Google Translate users the ability to hear how the words they’re seeing are supposed to be pronounced.
eSpeak uses a “formant synthesis” method, which according to the project’s page “allows many languages to be provided in a small size […] but is not as natural or smooth as larger synthesizers which are based on human speech recordings”.
Google first introduced its “text-to-speech” feature in November 2009, adding support for Hatian, Creole, French, Italian and German in recent months.
Today’s announcement adds text-to-speech functionality for for Afrikaans, Albanian, Catalan, Chinese (Mandarin), Croatian, Czech, Danish, Dutch, Finnish, Greek, Hungarian, Icelandic, Indonesian, Latvian, Macedonian, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Swahili, Swedish, Turkish, Vietnamese and Welsh.
As we noted last week when looking at the addition of translation using text recognition to Google Goggles, Google has been busy lately with numerous advances in the realm of translation. The company has announced automated captioning for YouTube videos, auto-translation for websites in Chrome and software to provide real-time voice translation over mobile phones.
