If you have already tried out the Google Assistant voice assistant available on all devices with Android Marshmallow and above, then you could note the high speed and accuracy of speech recognition. From now on, this technology is available to a wider range of users. Google announced that the APIs responsible for speech recognition in Google Assistant are now in the public domain, and all interested developers can use these tools in their applications.

Cloud Speech API for today supports work with 80 different languages.

Moreover, the technology uses machine learning, so over time, the accuracy and speed of speech recognition will only get better. Cloud Speech API also allows you to convert audio to text documents. Google even launched a special website where you can evaluate the capabilities of this technology in action.

The emergence of the Cloud Speech API in open access will allow third-party developers to apply speech recognition technology in their applications. It can be services for converting audio to text, voice control systems in cars and much more.