There are no active ads.


Google’s Cloud Speech API now understands Urdu (and more!)

by Josh Levenson | August 15, 2017August 15, 2017 3:30 pm PDT

Google has announced that it’s updated its Cloud Speech API with support for thirty additional languages, including Bengali, Georgian, Latvian, Tamil, Telugu and Urdu.

To incorporate the new languages, the firm collected speech samples from natives, then fed them to a machine that—somehow— trained itself to understand the words.

  • Amharic (Ethiopia)
  • Armenian (Armenia)
  • Azerbaijani (Azerbaijani)
  • Bengali (Bangladesh, India)
  • English (Ghana, Kenya, Nigeria, Tanzania)
  • Georgian (Georgia)
  • Gujarati (India)
  • Javanese (Indonesia)
  • Kannada (India)
  • Khmer (Cambodian)
  • Lao (Laos)
  • Latvian (Latvia)
  • Malayalam (India)
  • Marathi (India)
  • Nepali (Nepal)
  • Sinhala (Sri Lanka)
  • Sundanese (Indonesia)
  • Swahili (Tanzania, Kenya)
  • Tamil (India, Singapore, Sri Lanka, Malaysia)
  • Telugu (India)
  • Urdu (Pakistan, India)

Google’s ventured into a huge market

With this expansion, Google expects its Cloud Speech-powered applications, like Gboard and Google Translate, to reach more than a billion new customers in Asia.


Josh Levenson

Josh Levenson is an avid technology enthusiast who writes news and the occasional how-to. He's also a self-proclaimed sneakerhead and has been an...