Customizable voice assistant
Project description
Voice Assistant
Customizable voice assistant (README.md to be completed)
Features
- Trigger word can be said anywhere in a sentence, for example, "play music, Jarvis". It relies on Picovoice porcupine
- Speech-to-Text relies on Google Cloud Speech-To-Text API
- Text-to-Speech relies on Amazon Polly
Installation
-
Install Docker with official guide or use convenience script (currently the only option for Raspbian): Uninstall old versions
sudo apt-get remove docker docker-engine docker.io containerd runc
Install using convenience script
curl -fsSL https://get.docker.com -o get-docker.sh sh get-docker.sh
-
Create a folder to store configuration files e.g.
mkdir ~/.voice-assistant
-
Set up Google Cloud Speech-To-Text
- Create Google Cloud Platform project and download your credentials following instructions
- Put credentials into your configuration folder
~/.voice-assistant/google_credentials.json
- Activate Cloud Speech-To-Text API for your project
-
Set up AWS for Text-to-Speech Create AWS account and take a note of Access Key ID and Secret Access Key
-
Add
configuration.yaml
into~/.voice-assistant/configuration.yaml
:google_cloud: language_code: "en-US" aws: access_key_id: "YOUR_ACCES_KEY_ID" secret_access_key: "YOUR_SECRET_ACCESS_KEY" region_name: eu-west-2 # set closest to your location voice_id: "Brian"
- Build Voice Assistant on Docker
sudo docker build -t voice-assistant .
Run on Docker
For convenience Docker Compose can be used:
Create docker-compose.yaml
:
version: '0.0.1'
services:
voice-assistant:
container_name: voice-assistant
image: voice-assistant
volumes:
# volume to share config and credentials from host to container
- your/configuration/folder:/usr/src/config
devices:
# sounds devices need to be exposed to container
- /dev/snd:/dev/snd
restart: always
Then run with sudo docker-compose up
in the same folder.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for voiceassistant-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e9a849a447fc6b0342ee0bc8d956b03b88cb92aabe14545670aae8c72ea39823 |
|
MD5 | ba0e669b91e2d5e06ca86536cea40030 |
|
BLAKE2b-256 | 4541c28bddacb672345061d4179329a7412e267c3b7c767a5cae2d95e28f0066 |