This is the forum archive of Homey. For more information about Homey, visit the Official Homey website.
The Homey Community has been moved to https://community.athom.com.
This forum is now read-only for archive purposes.
The Homey Community has been moved to https://community.athom.com.
This forum is now read-only for archive purposes.
Closed
Voice training
I was wondering about the voice training.
When I started using Homey, it didn't understand the trigger at all.
Then I trained my voice (which did not go very well I have to say). After that, the trigger is pretty much OK, but the recognition is pretty bad (and my English is OK).
When my family came home, my kids wanted to try it also ofcourse. Result, trigger is not recognized.
My daughter trained her voice, after that the trigger only worked for her.
After I read that another user trained it together with his girlfriend, I tried this with my family (I used 2 attempts, my wife and kids the 3 other). Again, this took a long time to succeed.
Now Homey reacts to almost every sound it hears. And I've had 3 times already a 'Oops, I couldn't reach the server'.
How should we train Homey? Or do I have to wait until you received enough trainings to adjust the trigger recognition?
If so, will this be updated on Homey automatically?
When I started using Homey, it didn't understand the trigger at all.
Then I trained my voice (which did not go very well I have to say). After that, the trigger is pretty much OK, but the recognition is pretty bad (and my English is OK).
When my family came home, my kids wanted to try it also ofcourse. Result, trigger is not recognized.
My daughter trained her voice, after that the trigger only worked for her.
After I read that another user trained it together with his girlfriend, I tried this with my family (I used 2 attempts, my wife and kids the 3 other). Again, this took a long time to succeed.
Now Homey reacts to almost every sound it hears. And I've had 3 times already a 'Oops, I couldn't reach the server'.
How should we train Homey? Or do I have to wait until you received enough trainings to adjust the trigger recognition?
If so, will this be updated on Homey automatically?
This discussion has been closed.
Comments
Also I noticed, not sure if it is related, that I'm not able to trigger a voice output. I tried custom flows that I could trigger, but never did I get any audio response. The only time I hear the homey saying something is when I click on the preview button in the voice selection.
Apparently, when the command isn't understood, nothing happens... I think this should be changed.
When the service is not available, you get a voice output 'Oops, couldn't reach the server, try again later'
Edit:
After that I reloaded the page to cancel the voice training as I didnt want my cough to be a trigger and now when I want to train again it says "already learning".
How to reset this?
Before at a distance of 3-4 meters the voice recognition didn't work for me quite well (20 tries without success).
This time I started voice training at 4-5 meters and got 5 out of 6 passes .