With the introduction of voice search to 30 new languages, Google has made this feature accessible to over one billion people globally.
In total, Google’s speech recognition now supports 119 languages. Additionally, it now recognizes emoji language.
This means you can now dictate emojis in US English with phrases like “winky face emoji,” “smiley face emoji,” and “tongue out emoji.”
Bringing Voice Search to Global Users
Google aims to “honor languages around the world,” which includes the ancient Georgian language that dates back to the 10th century.
”We’re also adding Swahili and Amharic, two of Africa’s largest languages, as well as many Indian languages on our mission to make the internet more inclusive.”
Google’s list of newly supported languages includes:
- Amharic (Ethiopia)
- Armenian (Armenia)
- Azerbaijani (Azerbaijan)
- Bengali (Bangladesh, India)
- English (Ghana, Kenya, Nigeria, Tanzania)
- Georgian (Georgia)
- Gujarati (India)
- Javanese (Indonesia)
- Kannada (India)
- Khmer (Cambodia)
- 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 highlights that it has collaborated with native speakers to collect speech samples for these new languages by asking them to recite common phrases.
”This process trained our machine learning models to understand the sounds and words of the new languages and to improve their accuracy as they are exposed to more examples over time.”
Besides voice search, these new languages are also available in Google’s Cloud Speech API and will soon be incorporated into other Google products.
