Google opens speech recognition API in 80 languages.
![](https://habrastorage.org/files/b33/a35/7ff/b33a357ff88d4741a14add08cecca984.png)
Speech recognition works for 80 languages. It is possible to recognize speech live through a microphone or audio recordings from files (probably up to 2 minutes ). Numerous formats are supported, including FLAC, AMR and PCMU.
Now for any program you can embed, for example, voice control through the Cloud Speech API. The system displays the recognized text instantly in the process.
Google claims that the Speech API works quite accurately even with a noisy background, so the material does not need to be pre-cleaned by processing with filters or using expensive equipment and microphones for noise cancellation.
Some languages support automatic filtering of inappropriate content.
Rumors about the opening of interfaces have been going in the last few weeks. Experts expressed the opinion that Google is going to enter the market, where Nuance and some other companies specializing in speech recognition are now operating. Now it will be hard for them to use Google, its system uses the latest developments in the field of self-learning neural networks - the same engine as Google’s voice search and voice dialing from Google keyboard. Every month Cloud Speech API will recognize the text more and more accurately.
The company announced the news about Cloud Speech API yesterday at the NEXT conference . In addition to speech recognition, developers now have access to the Cloud Machine Learning machine learning platform .
The opening of the Google Voice Recognition API will hit not only specialized companies, but also Apple, whose Siri voice assistant is significantly inferior to Google’s neural network in recognition accuracy and functionality.