Krdytkyu

I would like to enable a system that can respond to user voice commands and run scripts according to the verbal command GIVEN.

Ideally, I would like for the computer to be listening constantly.

Once it hears the buzz word "Computer" it will activate and listen for commands for 10 seconds (or so).

Once active, and while it's listening, I would like for another set of buzz words to be able to run scripts.

For instance....

(Computer is idle) "Computer" (computer immediately listens) "Access new MESSAGES" (MESSAGES being buzz word *IGNORES "ACCESS NEW" -- computer runs a script and opens evolution or empathy). There could be one for browser, one for closing windows and showing desktop, or a bunch of stuff really.

Is this even possible?

Gnome-Voice-Control

Developed as part of Google Summer of Code 2007, this was an idea to develop some features that will improve the usability in the Gnome Desktop.

The goal is to implement a Desktop Voice Control System. The system
consists in an application that will be monitoring the audio
input(microphone) and when a significant audio signal has been
detected, the software catches, processes and recognizes the signal
and then executes the desired action over the Gnome Desktop. In a set
of actions could include maximize, minimize, close the active window;
open a specific program; switching from one desktop to another; among
others. GnomeVoiceControl is implemented in C in conjunction with CMU
Sphinx, which is an open source tool, created to convert speech to
text.

Slide-show by the authors

Unfortunately it looks like it has not developed much beyond the basic "goals" - however there does appear to be some activity adding support for new languages such as Bulgarian and Turkish this year.

To install:

sudo apt-get install gnome-voice-control

Platypus

There is an interesting looking project call platypus - basically is a linux front-end to Dragon Naturally Speaking which runs in Wine.

The claim-to-fame for this application is "it can even launch Windows or Linux programs and scripts, e.g. "start terminal".

VEDICS

This is a newish project that says it works with the Unity interface.

The project page says it recognises "run [program name]" - so in theory you [program name] could be any script you want to run.

Simon Listens

This is an open source project aimed to replace mouse and/or keyboard by speech recognition initially developed for physically disabled people.

There is a ppa from where we can install the application: ppa:grasch-simon-listens/simon

Google2Ubuntu

Google2Ubuntu is a tool that lets you control your computer using voice commands via the Google speech recognition API.

Run the below commands on terminal to install google2Ubuntu,

sudo add-apt-repository ppa:benoitfra/google2ubuntu

sudo apt-get update

sudo apt-get install google2ubuntu

Source

Linux Speech Recognition

It is being developed to run under Linux distributions, it is very configurable and easy to extend, support custom dictionaries, context based recognition, dictation mode and configurable macros.

In order to install Linux Speech Recognition go to the project's GitHub page. Download the ZIP file and extract it.

Then install some dependencies:

sudo apt-get install sox python-argparse libsox-fmt-mp3 mutt xvkbd xautomation

Open the extracted folder (Palaver-master) in the terminal and execute the setup:

cd /~Path-to-folder~/Palaver-master/

./setup

Now it is just to assign a hotkey to enable recording, in order to do that go to System Settings... > Keyboard > Shortcuts > Custom Shortcuts click the Plus Button to add a shortcut, name it Voice Recognition and set the command to:

/~Path-to-folder~/Palaver-master/hotkey

Click apply, click over the shortcut and then assign a hotkey to activate Voice Recognition.

Notice that no stable build have been released yet, so don't expect commands to be fully functional at this stage, many phrases will be recognized, but no real action will be done.

Snips.ai

Just tried it on pi3 - seems to have potential

Runs in docker

https://snips.ai/