Kalliope assistant + MM

sispheor

@marcnlx take a look to starter kits. It contains example. Also there is an example of usage of each neuron on the website.
Have fun !

marcnlx

@sispheor said in Kalliope assistant + MM:

@marcnlx take a look to starter kits. It contains example. Also there is an example of usage of each neuron on the website.
Have fun !

I will! I’m going to check everything out later today, thanks!

marcnlx

I tested Kalliope yesterday night and once you know how it works, it’s pretty sweet! ;)

Unfortunately I noticed some bugs/issues which are discussed multiple times on Github, so for now I think I will wait until a later release since I need to restart Kalliope multiple times after 2-3 phrases because of pulseaudio issues which I can’t seem to fix:

2018-03-18 12:42:27 :: kalliope-0.5.1b :: File found in /home/pi/kalliope_starter_en/trigger/kalliope-EN-12samples.pmdl
Exception in thread Thread-2:
Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()

  File "/usr/local/lib/python2.7/dist-packages/kalliope-0.5.1b0-py2.7.egg/kalliope/trigger/snowboy/snowboydecoder.py", line 98, in __init__
    stream_callback=audio_callback)
  File "build/bdist.linux-armv7l/egg/pyaudio.py", line 750, in open
    stream = Stream(self, *args, **kwargs)
  File "build/bdist.linux-armv7l/egg/pyaudio.py", line 441, in __init__
    self._stream = pa.open(**arguments)
IOError: [Errno -9985] Device unavailable

sispheor

@marcnlx Uninstall pulse audio and work only with alsa.
We’ve remove pulseaudio from our doc.

sispheor

Kalliope v0.5.1 has been released with all stuff needed to integrate Magic Mirror.

maxbachmann

@sispheor kalliope uses the Google Speech recognition?

strawberry 3.141

@maxbachmann google is the default, but you can select others https://kalliope-project.github.io/kalliope/settings/settings/#speech-to-text-configuration

sispheor

@maxbachmann Yes you can choose your STT and TTS engine. Some are cloud based and some can be self hosted.

dmwilsonkc

@sispheor I am interested in duplicating your work for a different AI. So I figured the best place to start is to install your module and get it working before I make changes to suit my needs with the other AI. I have installed the MMM-Kalliope module, but the curl commands do not display on my mirror. I am not sure what I am doing wrong. Here’s my entry in config.js

{
    module: "MMM-kalliope",
    position: "upper_third",
                        config: {
                                max: "5",
                                keep_seconds: "8",
                                title: "Kalliope"
                                }

},

I do receive a json response indicating success, however, nothing gets displayed on the mirror.

Here’s the curl command:

curl -H "Content-Type: application/json" -X POST -d '{"notification":"KALLIOPE", "payload": "my message"}' http://localhost:8080/kalliope

Here’s the response:

{"status": "success"}

Yet nothing gets displayed. Do you have any suggestions?

sispheor

@dmwilsonkc seems good anyway.
I don’t see any errors. Maybe test another position. This one is not already used by another module?