Skip to content
This repository has been archived by the owner on Jul 31, 2021. It is now read-only.
Anton Yarkov edited this page May 17, 2020 · 9 revisions

Application is designed for voice recognition in real time and converting it into a text. It using Google Voice unpublished API. Basically it works as is: *1. You turn on your microphone *2. Press Start button *3. Talk something, for example, have a meeting in Skype *4. During your talk application switch audio channel on a small pieces and sends it to Google for recognition *5. Results is visible as text marks at the bottom Text field

The idea was to create something like LOGs for voice meetings, which could be automatically stored in memory more efficiently than audio. Additional bonus is possibility to search on your logs.

Also I was inspired to create this application because I wanted to learn WPF technology and learn how to make low level calls to WinAPI and drawing graphs of the audio channel.

P.S. 2014. For current moment it doesn't not work because Google changed its API to published officially and we need to switch to real API.

1

2

3

Clone this wiki locally