vasisualy Download - vasisualy Source code download

vasisualy

AI Source Code

1.0.0

Download

Voice assistant Vasisuali?

Vasisuali is a simple modular voice assistant, respecting your freedom, although it can be hagged: smile:. So far, only Russian is supported.

️ It is not recommended to use voice control (button located to the right of the text input field) in this version, in view of the use of speech from Google for this. If you want to use voice control and at the same time do not send your voice Google use this branch with a free offline speech recognition.

Supported platforms?

GNU/Linux (QT5 and CLI) ?
Microsoft Windows (poorly supported, and does not always work) ?
Android ?

Vasisuali can:

Say the current date and time.
Tell a joke.
To say about current weather in any city in the world.
Turn on the radio.
Open a browser or website (for example, YouTube).
Run the program installed on your PC.
Take a picture of the screen.
Search for information in an iternet.
Turn off or restart the computer.
Search for video on YouTube.
Repeat your words like a parrot.
Throw a coin.
Say the tongue twister.
Open cards (OpenStreetmap)
Search for the answer to your question on Wikipedia.
Say where you are.
Translate the text from any language into Russian, Spanish, English, French, Italian, etc.
Tell the news with Wikinews.
Play in guess the number and Russian roulette with you.
To communicate primitively.
And much more ...

Installation ?

GNU/Linux?

You can download Appimage, working in many distributions, from the release page.

Debian/Ubuntu

First you will need to install Rhvoice speech synthesizer:

 sudo add-apt-repository ppa:linvinus/rhvoice
sudo apt-get update
sudo apt-get install speech-dispatcher-rhvoice rhvoice-russian

Then you need to install the SpeechD module for Python, Pyqt5 and VLC using the package manager in your distribution (for example APT):

 sudo apt-get install python3-speechd python3-pyqt5 vlc python3-pyqt5.qtwebengine python3-pyaudio python3-vlc python3-alsaaudio

Clon this repository using Git:

 git clone --recursive https://github.com/Oknolaz/vasisualy
cd vasisualy

Next, you need to install other modules using PIP:

 pip3 install -r requirements.txt

After these actions, you can run the script with this command for the Qt GUI version:

 python3 run.py

Arch Linux

First you need to install the Rhvoice and Python-VLC modules from AUR. For installation using yay, use:

 yay -Sy rhvoice python-vlc

Install the necessary packages using Pacman:

 pacman -Sy python-pyaudio python-pyqt5 python-pyalsa speech-dispatcher qt5-webengine vlc python-pyqt5-webengine

Clon this repository:

 git clone --recursive https://github.com/Oknolaz/vasisualy
cd vasisualy

Then set the dependencies using PIP:

 pip3 install -r requirements.txt

After these actions, you can run the script with this command for the Qt GUI version:

 python3 run.py

AUR repository is also available

CLI for GNU/Linux

For a CLI version with speech recognition adapted for single -pay computers (Raspberry Pi, Orange Pi, etc.):

 git clone --recursive https://github.com/Oknolaz/vasisualy-pi
cd vasisualy-pi
python3 run.py

Windows?

You need to install the Python 3 and VLC Media Player interpreter. Then download this repository, unpack the downloaded archive and go to the program folder. After installing this - install the necessary Python modules using PIP:

 pip install -r requirements.txt

Next, just start the script by the command:

 python run.py

Congratulations to you! ?

Help the project?

If you want to help in the development of the program, you can open Issue and tell about errors, offer your ideas. Also, in the presence of the necessary skills, you can create your own skill for the voice assistant and add it to the official repository using this instruction.