Skip to content
MagicMirror module - Hotword detector with snowboy
JavaScript Shell CSS
Branch: master
Clone or download
Latest commit 47b24ce Aug 4, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
components 2.0.0 May 19, 2019
documents Update Jun 6, 2019
installer 2.0.0 May 12, 2019
recipes 2.0.0 May 17, 2019
resources 2.0.0 May 17, 2019
temp 2.0.0 May 11, 2019
trainer 2.0.0 May 12, 2019
LICENSE Initial commit Jul 9, 2018
MMM-Hotword.css 2.0.0 May 17, 2019
MMM-Hotword.js urgent fix for mistype. Aug 4, 2019 Merge branch 'master' into 2.0.0 May 20, 2019
node_helper.js fix: sequential command pattern not terminated issue Jul 18, 2019
package.json 2.0.1 May 20, 2019


MMM-Hotword is a hotword detector using snowboy. You can use this module to wake another voice assistant or to give a command to other module.




2.0.1 (2019-05-20)

  • Fix: issue of afterRecording couldn't stop
  • Add: afterRecordLimit to stop recording by force.

2.0.0 (2019-05-19)

  • Whole new build-up
  • Some annoying dependencies are removed.
  • Installer is provided. (installer/
  • Personal model trainer is provided. (trainer/
  • Continuous recording after hotword detection is supported (Now you can say like "Computer, volume up" without pausing between Computer and volume up)
    • This feature could be used with MMM-AssistantMk2 ver3.x(Not yet released, but will arrive soon)
    • Or you can use this feature with other AI or Speech-To-Text program.
  • Simple standalone commands could be available. (Without any Assistant or Speech-To-Text, you can make own voice commands with this module standalone.). Commands could be combined sequence (You can make "volume-louder" with voice models "volume" and "louder")
  • More universal models are added. (computer, subex, hey extreme and more.)
  • Hotword detected could be displayed on screen of MM.

How to update (From previous version 1.X)

  • You need to remove old MMM-Hotword directory then re-install from scratch again.
  • Configuration should be re-written. It is not compatible with old version.


Read documents/

(OPTIONAL) Get your personal model (.pmdl)

Instead using universal model, You can make your own personal model. (ex. Hey,Dude, volume up, ...) Read documents/

  • Personal model is dedicated to each specific vocal pattern. You cannot share your model with others.
  • Personal model should be created on target device and mic. It might not work on other device.

Or.. For universal model (.umdl)

Read documents/


Read documents


1.1.0 (2018-11-4)

  • notification configurable. (You don't need MMM-NotificationTrigger any more for using with MMM-AssistantMk2(^2.0.0))
  • But if you want more complex action chains, you can still use MMM-NotificationTrigger also.

Last Tested; (2019-05-19)

  • MagicMirror : v2.7.1
  • Tested Environment :
    • Raspbian Stretch (Raspbian 3B+) / node v8.16.0 / npm v6.4.1
    • TinkerOS (TinkerBoard)
    • Ubuntu 18.04 (NVIDIA Jetson Nano)
    • OSX 10.14.4 (Apple MacBookPro) / node v11.12.0 / npm v6.7.0
You can’t perform that action at this time.