2

I know WebkitSpeechRecognition is only available on the chromium browser. However I am wondering how it converts the voice into text?

I tried to monitor the network log from developer console on the Google Chrome and I don't see any network activity. I thought I would send API request to the Google but I really don't.

I cannot find any architectural document on this either.

Does any one has any idea?

Paresh Varde
  • 1,084
  • 3
  • 16
  • 39
  • upon looking network traffic on Telerik Fiddler I see that it does communicate with Google API. However it turns back with bad Request! – Paresh Varde Oct 05 '16 at 09:40

1 Answers1

2

to my knowledge, there is no official documentation for the Google Speech API that is used in Chromium, but it has been "reversed engineered" by inspecting Chromium's source code

when you search for it, you should find multiple blogs / tutorials that describe, how the REST API can be used

a good description on how to use it, can be found here

http://blog.travispayton.com/wp-content/uploads/2014/03/Google-Speech-API.pdf

(with regard to the description in the PDF: the mentioned "Speech API V1" is deactivated by now, so only the "Full-Duplex API" can be used)

But note, that you need an API key via Google's Developer Console (for the Speech API); and for that you need to be registered in the Chromium Development Group. Also, using your own key, as of now, the Speech API it is limited to 50 transactions per day.

russa
  • 399
  • 3
  • 7