This library used to bring speech recognition to your Processing applications. Due to limitations in the involved speech to text API, the library has been replaced by a workaround that involves Google Chrome.
As of December 2014, further development has been discontinued. Looking for the old library?
Using WebSocket, Google Chrome and Processing, you can get unlimited speech recognition results in your Processing sketch.
Check out the example below to get started.
Install the WebSockets Library and create a new sketch with the example source code. Open this CodePen to start the voice recording in your Chrome web browser. Transcribed speech recognition results will now be sent to the running Processing Sketch and printed to the console.
If you don’t want to use the CodePen example, you can create your own HTML/JS file and access it from your own server or localhost.
I’m interested in the topic of speech recognition and natural language interfaces. Here are some things I did in that regards:
Article on pro-active personal assistants
A to-do list that gets it done for you
Talk at WebTuesday, 03/2015
Talking to Machines
Florian Schulz, June 2011–2017