We recommend using the images we provide. Those images are based on Raspbian, with a few customizations and are tested on the Raspberry Pi 3. If you prefer to setup Raspbian yourself, there are some manual steps you need to take.
First, make sure you have git
installed and clone this repository in
~/AIY-projects-python
:
sudo apt-get install git
cd
git clone https://github.com/google/aiyprojects-raspbian.git AIY-projects-python
Then, install the project dependencies and setup the services:
cd ~/AIY-projects-python
scripts/install-deps.sh
sudo scripts/install-services.sh
To use the Voice HAT, your kernel needs to be 4.9 or later. This is available on Raspbian 2017-07-05 and later. You'll also need to configure ALSA:
sudo scripts/configure-driver.sh
sudo reboot
After your Pi has rebooted with the driver enabled, run:
cd ~/AIY-projects-python
sudo scripts/install-alsa-config.sh
python3 checkpoints/check_audio.py
sudo reboot
Don't skip running check_audio.py
before rebooting, as it has an important
effect on the state of ALSA, the sound architecture.
To access the cloud services you need to register a project and generate credentials for cloud APIs. This is documented in the setup instructions on the webpage.
If you edit the code on a different computer, you can deploy it to your Raspberry Pi by running:
make deploy
You can find sample scripts in the src
directory showing how to use the
Assistant SDK.
To execute any of these scripts on the Raspberry Pi, login to it and run (replacing the filename with the script you want to run):
cd ~/AIY-projects-python
source env/bin/activate
python3 src/assistant_library_demo.py
If you want the voice recognizer service to run automatically when the Pi
boots, you need to have a file in the src
directory named main.py
. You can
make a copy of one of the sample scripts and rename it. Then run this command:
sudo systemctl enable voice-recognizer.service