Project Alias

136K381180

Intro: Project Alias

Alias is a teachable “parasite” that is designed to give users more control over their smart assistants, both when it comes to customisation and privacy. Through a simple app the user can train Alias to react on a custom wake-word/sound, and once trained, Alias can take control over your home assistant by activating it for you.

In this instructions, we will walk you through the main steps to complete your own Alias and start training a new wake-up-word for your smart device.

STEP 1: Requirements and Materials

The main components used in this build are:

Tools needed for this project are:

  • Access to a 3d printer
  • Soldering iron
  • Wire stripper
  • Screwdriver
  • A way to flash a micro SD card on your computer

Note: this project has only been tested with these components.

STEP 2: 3D Printing the Shell

For this step, we will be 3D printing the shell

For now, we have provided 2 options:

  • Google Home (original)
  • Amazon Echo

1. Print the shell and speaker holder in any color on a 3D printer. Because of the mesh in the object, it is important to keep the support material at a minimal. We had the best result printing it on its back-side. (See picture)

2. Use sandpaper to give the shell a nice and smooth surface. (optionally give it an acetone bath)

STEP 3: Wiring and Assembly

Before assembling the Alias we need to connect the speakers to the ReSpeaker audio shield and a power supply to the Raspberry Pi.

1. The speaker wires are stripped and soldered on to a JST 2.0 connector or an old Jack cable. The speakers and wires snap into the 3D printed speaker holder. (See picture above).
Note: We have found that the wires could trigger the Google Home when placed in the center. So for a better result on a Google Home try to route the wires down the sides.

2. Next, we need to supply 5V to the Raspberry Pi. Since there is not much space inside the shell, we decided to solder the 5V and Ground to the GPIO pins directly. You could try with an angled or modified micro USB cable. There is a small dent in the shell to route the wire out. Depending on your wire some fitting may be required.

3. Mount the speaker holder and Raspberry Pi to the shield with 4 small wood screws. (Tighten gently to prevent the 3D print to crack)

4. Place the assembled Alias on your device. If the fit is not smooth give the inside edge some sandpaper. It's important to align the speakers with the microphones of your device.

STEP 4: Software

In this step, we will be adding the software to the Raspberry Pi.

Please follow the steps on the projects GitHub page.

The code is set to be used with a Google Home from default. If you plan to use it on an Amazon Echo please change line 21 in app.py to use the alexa.wav file.

Amazon: sound.audioPlayer("data/alexa.wav",0,"wakeup", False)

Google Home: sound.audioPlayer("data/google_home.wav",0,"wakeup", False)

STEP 5: Train and Calibrate

In this step, we will train Alias with a custom wake-up word.

1. To train Alias, use the browser on your phone and open raspberrypi.local:5050

2. Hold down the record button while saying the new name about 4-6 times. A small bar should indicate the 2 seconds recording window. Each name should fit within this timeframe.

3. Under the menu, click Train Alias and wait a few seconds for the model to learn the name. This name does not necessarily need to be a word but can be a sound and any language. So be creative! You can always reset your name on the menu. Tip: it helps to record the name from different locations in your home.

4. Try it out! Say the name and ask your question once you see a blue light on the device or on your phone.
Note: once trained there is no need to have the phone connected anymore.

If you find Alias is not responding correctly, try to train a few more examples. Or if you find Alias is triggering to often, you can go to the menu and turn background sound ON. This toggles the background mode and adds any new recordings to the background examples. Record and train just as before, but try to capture unique sounds in your environment or even words that sound similar to your chosen name.

105 Comments

Is it possible to specify the steps around "Wiring and assembly" a bit more? Where do I have to connect the wires of the speaker exactly, for instance?
Thanks in advance,
Hi,

its December 2023 and I'm wondering if this project still works?
will I be able to get the code to work?
I have spare RPi3s and a google home mini.
any chance the original google home print fits a Pi3 and a home mini?
Hey there. I love the project, but I have newer devices - any chance to get new printing models?
Greetings
Hello thank for this great share. I face a little problem . I follow all of theses points and managed to do it. Yet none of Word are recognized ( as if micro don’t work on ReSpeaker 2-Mics Pi HAT.
Any idea please ? ( i heard nose but never stop, i did n’y do vocal training but if i anderstand well not needed now. Whatever i say never stop .)
Going to keep researching and trying, likely over next few weekends. Will document what I have tried so far in this thread.

1. I used the Easy Setup Method from the Github Page. I am able to observe the yellow light and in general have the speakers working correctly.
2. I can type in alias.local or "IP address of the pi" and it will bring me to the setup pages that look like this https://github.com/bjoernkarmann/project_alias/blo...
3. The speakers are outputting white noise and I can add new commands using the alias.local which it will then run, I just can't get to the training section like we see on step 5 on this page
4. Typing in raspberrypi.local or raspberrypi.local:5050 causes a timeout.
5. Putting my computer on the alias wifi network, I was able to PuTTY in with the IP address. raspberrypi.local and alias.local don't work in typing in the Host Name or IP address for PuTTY but 192.168.4.1 does.
6. When I run sudo apt-get install avahi-daemon it says its already installed, but I thought this is what allows us to get in raspberrypi.local? So it should hypothetically already be working.
7. I want to use avahi-browse --all to see what the active avahi configuration is but "command not found"
8. So I need to sudo apt-get install avahi-utils, but it can't because this isn't installed already and the pi isn't connected to the internet so it can't get this command
9. So next steps will be to figure out how to connect the pi to the net, get this update and then see what the avahi configuration is?

Open to suggestions
I found this thread very helpful
https://www.raspberrypi.org/forums/viewtopic.php?t=61368

Other ideas:
Does the manual install method fix this?
Changed my DNS server from automatic to Google (8.8.8.8) - didn't work

You should be able to connect to the Project Alias wifi and then go to 192.168.1.1 and see the provided page from the Pi. I wrote up a bunch of things lower in the comments hope they help. Have fun and keep on making.
Heck yeah! I'll try this out when tinkering this weekend, excited!
Awesome project, Thanks for sharing. I have watched this project since you first shared it and I finally decided it was time to make it. It worked first try after reading some of the tips in the comments. Here is what I found helped.
Buy the speakers from DIGI. They ship fast (in the US) and aren't expensive. Ebay has them but they all take a few months to get from other countries.
A 4GB SD card will work.
Once it's put together follow the Easy setup instructions on the Github page for the software setup.
The setup page that is served from the raspberry pi doesn't have the big record button anymore. Now all you need to do is enter the text of what you want to use as the new wake word. Once you connect to the WIFI of the Pi you can use 192.168.1.1 to change the settings if you can't connect the way they provide.
There is a little glitch i found that the screen goes blank when you want to enter the new words but if you type it still takes.
It does have false activations but my google home mini just lights up and waits for a question or comment but so does the Mini and my Alexa with their normal wake words.
Overall it is a really easy project if you take your time and check what others note in the comments. Good luck and keep on MAKING!

UPDATE> I am seeing a few people have issues with a Pi 4. I know other programs need to be recompiled for the Pi 4 and i don't believe this program has had that done. I have mine running on a Pi 3A and it works fine.

UPDATE 2 12/17/20 > I have moved the project to a Pi zero W and it works fine without having to recompile. I actually use this is a car on a project that i am working on. The car is old and a little noisy so i am playing with the mic sensitivity to see if it will pick up the wake word better. Other then that is is a really easy to use project.
Thanks for mentioning it doesn't have the record button anymore, does that mean it doesn't need to be trained?
Yes that is true. I was prepared to do the training part of the setup but it just wanted the phrase typed in and it worked on the first try. There is mention in the Github that they have a speach recognition software that seems to be a new edition. It's pretty easy to make it work all around as long as you are diligent and patient. Good luck. It's a lot of fun to get working.
UPDATE: After 10 months this is still working fine. I moved to a Pi Zero W too.
Also on the Pi Hat you can use a small speaker if you want. I used a tiny keychain speaker that has a USB charger built in. The tiny speakers recommended are great but the wires connected to them are very delicate.
Since it has its own web page built in i can adjust the sensitivity on the fly as well. But i don't normally need to.

I plan to make a few more now and have them on all my smart speakers so i can call them all the same thing.
Did you use one of the shell templates from the tutorial or did you make your own?
At this time I did not make my own or use theirs. I am makeing one though but its working at the moment with tape
I'm having trouble finding the RPi's WiFi network on my phone - does it need to be initialized somehow?
No it should already be visible after a minute or so from turning it on. Be sure to have a Pi3A or older. I think there maybe something not right with the software running on the Pi 4. You should be able to see a wifi name of "Project Alias" and connect to it. It will not have internet access but you will be able to connect to 192.168 .1.1
Good luck
I have been using it for a little over a week now. I use the wake word Huey and it doesn't seem to wake when not called. The only draw back i have found is there is a longer then apprieciated delay between the time i say Huey till the time it activates the Nest mini. I'm sure there is a way to speed this up in the code so i am looking into it but i am not a coder so it may be slow going.
If anyone needs CAD help or for me to create / 3d print/ both... just message me. I use to do CAD for a living... so I am ok with it.lol
Any chance you'd be willing/able to do a Google Home Mini design?
Hey man, shoot me a direct message. Let me know what all you are trying to do...
More Comments