About
speech recognition to control your OS
kiku means “listen” in Japanese. it aims at saving time and pain (voice instead of mouse & keyboard). you should look at the video section to have an idea of what kiku can do for you. basically:
- English acoustic model (provided by VoxForge)
- Japanese acoustic / language model (provided by Julius)
- German acoustic model (provided by VoxForge)
- Portuguese acoustic / language model
- emulate the keyboard and the mouse (provided by xdotool)
- open sound control client (send recognition result or any message via udp / tcp)
- use PulseAudio or Alsa
- monitor processes to load the matching V2C (voice to command)
- automatic pausing / unpausing
- notification using: libnotify, libxosd, built-in
