On my way to my own Mark-IIr
3D printing of housing is finished. Now some glueing and soldering while start-stop-watching the assembly video
A big thank you to @derick-mycroft for providing the STL files!
4 Likes
Very cool !
Which screen did you choose?
This a Mark-IIR which does not have a built-in screen.
When everything works out fine i am planning to add a Waveshare 4.3" LCD (the same that is used for the Mark-II-RPI)
Ah, right! Didn’t do my homework 
Hope to get my hand on one of those boards myself sooner then later. Read good things about it. Looking forward to you build log 
First of all, thank you for the hard work Dominik 
,
I have the problem that the respeaker core v2 doesn’t record, the mic and bluetooth speakers working fine, the mic Level goes up and seems to be fine and I checked alsamixer too.
I have to mention after the first Installation it worked fine, but on the next morning when I started the respeaker it didn’t work anymore properly and I didn’t change anything.
When I start the debug Mode, it doesn’t show any error I don’t know what to do or where to look :).
Can please someone help me i’m a beginner, thanks :).
Hi Dominik,
Also want to thank you for your great work.
I’ve had a respeaker core V2.0 for over a year and wanted to use it on a robotics command and control project I’ve been working on for a while.
Mycroft has come a long way and seems like a great active project, which is why I thought it would be great to try installing it on the respeaker core V2.0.
I worked through your installation instructions, and it seemed to be working, but then it stopped once it was authenticated to the main server.
I now start it and get nothing, not even errors.
When I run the pulse audio test, it seems to record a file, but can not play.
It seems like the problem is with pulse audio, but I’m not sure where to start.
Thanks in advance!!!
2 Likes
Hi again,
I just reinstalled the respeaker package and that fixed things.
Not sure what happened, but I’m all good now.
1 Like
Good to hear a fresh install got it working.
Interested to see the broader project you’re working on sometime too
A quick look at the robot. Charlie.
Hopefully voice commands will control most of the behavior.
3 Likes
Damn that looks like a beast! Looking forward to seeing it evolve
Hi guys.
I’m having totally a lot of fun with the mycroft project now. Its awesome and runs well on my respeaker core V2.0.
I am having a little issue here, though…
I want to install a custom wake-word for the robot, and fudging around with precise looked a little daunting, so I am trying snowboy.
starting with the default snowboy.umdl file, and just altering the config. here is what I did…
“listener”: {
“wake_word”: “snowboy”
},
“hotwords”: {
“snowboy”: {
“module”: “snowboy”,
“local_model_file”: “home/respeaker/.mycroft/snowboy.umdl”,
“sensitivity”: 0.1
}
},
It seems to be using snowboy now, but the problem is that it is triggered all the time.
Any little sound triggers the wake up, even when I reduce the sensitivity down to 0.1.
If anyone have played around with snowboy, this would be a great help, thanks in advance
OK, so I abandoned my quest to make snowboy work, and decided to use the CMUsphinx instead.
It mostly works, but it really was a necessity to get my robot to respond to its own name!
Here are the results:
1 Like
Wow, very cool!
I plan on building a Spotmicro, most likely in the OpenQuadruped design. Like Charlie robot with Mycroft integration of course.
2 Likes
Are you happening to use ROS for your robot? I’m building my own robot and am looking for a solution to integrate mycroft with ROS. There’s one package that I’ve found, http://wiki.ros.org/mycroft_ros, but it hasn’t had much love lately. I’m not sure there are others.
Yes, my Open-Quad robot will run with ROS - I am a ROS novice though. Thanks for the pointer to Mycroft-ROS.
Same here… its a bit of a big learning curve, but slowly I’m getting there. I finally have it reliably navigating through the doorway and down the hall. It’s my third generation build since the beginning of the year and it runs much better. Here’s a video of it (I had to blur family photos or my wife wouldn’t let me post it publicly)… cables are messy because its temporary installation until I get a Rock Pi X to run everything on it.
1 Like
I’m having an issue with the install. I followed the directions as precisely as I can (twice) and both times after running:
cd ~/mycroft-core
./start-mycroft.sh debug
I get the following error message:
respeaker@v2:~/mycroft-core$ ./start-mycroft.sh debug
Already up-to-date.
Starting all mycroft-core services
Initializing…
Starting background service bus
CAUTION: The Mycroft bus is an open websocket with no built-in security
measures. You are responsible for protecting the local port
8181 with a firewall as appropriate.
Starting background service skills
Starting background service audio
Starting background service voice
Starting background service enclosure
Starting cli
Traceback (most recent call last):
File “/usr/lib/python3.5/runpy.py”, line 193, in _run_module_as_main
“main”, mod_spec)
File “/usr/lib/python3.5/runpy.py”, line 85, in _run_code
exec(code, run_globals)
File “/home/respeaker/mycroft-core/mycroft/client/text/main.py”, line 21, in
from .text_client import (
File “/home/respeaker/mycroft-core/mycroft/client/text/text_client.py”, line 21, in
from mycroft.tts import TTS
File “/home/respeaker/mycroft-core/mycroft/tts/init.py”, line 20, in
from .tts import TTSFactory, TTS, TTSValidator, PlaybackThread
File “/home/respeaker/mycroft-core/mycroft/tts/tts.py”, line 467, in
class TTSFactory:
File “/home/respeaker/mycroft-core/mycroft/tts/tts.py”, line 473, in TTSFactory
from mycroft.tts.mimic_tts import Mimic
File “/home/respeaker/mycroft-core/mycroft/tts/mimic_tts.py”, line 40, in
import distutils.spawn
File “”, line 969, in _find_and_load
File “”, line 958, in _find_and_load_unlocked
File “”, line 666, in _load_unlocked
File “”, line 577, in module_from_spec
File “/home/respeaker/mycroft-core/.venv/lib/python3.5/site-packages/_distutils_hack/init.py”, line 82, in create_module
return importlib.import_module(‘._distutils’, ‘setuptools’)
File “/usr/lib/python3.5/importlib/init.py”, line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File “”, line 981, in _gcd_import
File “”, line 931, in _sanity_check
SystemError: Parent module ‘setuptools’ not loaded, cannot perform relative import
respeaker@v2:~/mycroft-core$
Any suggestions?
There was recently a major update to mycroft-core (20.2.5), maybe that did break something - I haven’t fired up my RC2 in the last few days, so I might have missed some incompatibility - will check that later…
found this solution:
export SETUPTOOLS_USE_DISTUTILS=stdlib
from this page:
1 Like
So I have some new issues. I’m having a hard time getting it to survive a reboot. I started from scratch and just loaded respeaker after getting connect to the network (no upgrade/update because for whatever reason, doing so breaks firefox), made the configuration changes, and did an audio test and it works. If I reboot, and do the audio test, it seems to record something, but its squeaks instead of clear voices. Any idea what could be going wrong?