This part of the documentation explains the main configuration of Kalliope.
Kalliope needs two files to works, a settings.yml
and a brain.yml
. Files are written on YAML syntax.
When you start kalliope using the CLI, the program will try to load your settings.yml and brain.yml in the following order:
/home/pi/my_kalliope/settings.yml
/etc/kalliope/settings.yml
settings.yml
. You can take a look into the default settings.yml
file which is located in the root of the project tree.This a common tree of a Kalliope configuration folder:
kalliope_config/
├── brains
│ └── included_brain.yml
├── brain.yml
├── files
│ └── kalliope-FR-13samples.pmdl
└── settings.yml
The trigger is the module detecting the hotword that will wake up Kalliope. Common usage of hotword include Alexa on Amazon Echo, OK Google on some Android devices and Hey Siri on iPhones.
Specify the name of the trigger module you want to use.
default_trigger: "trigger_name"
Available triggers for Kalliope are:
The hotword (also called a wake word or trigger word) detector is the engine in charge of waking up Kalliope.
Each Trigger has it own configuration. This configuration is passed as argument following the syntax bellow
triggers:
- trigger_name:
parameter_name: "value"
E.g, the default Snowboy trigger configuration is
triggers:
- snowboy:
pmdl_file: "trigger/snowboy/resources/model.pmdl"
See the complete list of available triggers here.
A Speech To Text(STT) is an engine used to translate what you say into a text that can be processed by Kalliope core. By default, Kalliope uses google STT engine.
The following syntax is used to provide the engine name:
default_speech_to_text: "stt_name"
E.g
default_speech_to_text: "google"
Get the full list of SST engine here.
Each STT has it own configuration. This configuration is passed as argument as shown bellow
speech_to_text:
- stt_name:
parameter_name: "value"
E.g:
speech_to_text:
- google:
language: "fr-FR"
- bing
Some arguments are required, some others are optional, please refer to the STT documentation to know available parameters for each supported STT.
A Text To Speech is an engine used to translate written text into a speech, into an audio stream. By default, Kalliope use Pico2wave TTS engine.
The following syntax is used to provide the TTS engine name
default_text_to_speech: "tts_name"
Eg
default_text_to_speech: "pico2wave"
Get the full list of TTS engine here.
Each TTS has it own configuration. This configuration is passed as argument following the syntax bellow
text_to_speech:
- tts_name:
parameter_name: "value"
E.g
text_to_speech:
- pico2wave:
language: "fr-FR"
- voxygen:
voice: "michel"
Some arguments are required, some other optional, please refer to the TTS documentation to know available parameters for each supported TTS.
When Kalliope detects your trigger/hotword/magic word, it lets you know that it's operational and now waiting for order. It's done by answering randomly one of the sentences provided in the variable random_wake_up_answers.
This variable must contain a list of strings as shownbellow
random_wake_up_answers:
- "You sentence"
- "Another sentence"
E.g
random_wake_up_answers:
- "Yes sir?"
- "I'm listening"
- "Sir?"
- "What can I do for you?"
- "Listening"
- "Yes?"
You can play a sound when Kalliope detects the hotword/trigger instead of saying something from
the random_wake_up_answers
.
Place here a list of full paths of the sound files you want to use. Otherwise, you can use some default sounds provided by Kalliope which you can find in /usr/lib/kalliope/sounds
.
By default two file are provided: ding.wav and dong.wav. In all cases, the file must be in .wav
or .mp3
format. If more than on file is present in the list,
Kalliope will select one randomly at each wake up.
random_wake_up_sounds:
- "local_file_in_sounds_folder.wav"
- "/my/personal/full/path/my_file.mp3"
E.g
random_wake_up_sounds:
- "ding.wav"
- "dong.wav"
- "/my/personal/full/path/my_file.mp3"
**Note: ** If you want to use a wake up sound instead of a wake up answer you must comment out the
random_wake_up_answers
section. E.g:# random_wake_up_answers:
A Rest API can be activated in order to:
For the complete API ref see the REST API documentation
Settings examples:
rest_api:
active: True
port: 5000
password_protected: True
login: admin
password: secret
To enable the rest api server.
The listening port of the web server. Must be an integer in range 1024-65535.
If True
, the whole api will be password protected.
Login used by the basic HTTP authentication. Must be provided if password_protected
is True
Password used by the basic HTTP authentication. Must be provided if password_protected
is True
Run a default synapse when Kalliope can't find the order in any synapse.
default_synapse: "synapse-name"
E.g
default_synapse: "Default-response"
The resources directory is the path where Kalliope will try to load community modules like Neurons, STTs or TTSs. Set a valid path is required if you want to install community neuron. The path can be relative or absolute.
resource_directory:
resource_name: "path"
E.g
resource_directory:
neuron: "resources/neurons"
stt: "resources/stt"
tts: "resources/tts"
trigger: "/full/path/to/trigger"
Now your settings are ok, you can start creating the brain of your assistant.