Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/Harsha200105/DesktopAssistant/llms.txt

Use this file to discover all available pages before exploring further.

Desktop Assistant supports two platforms — Windows and Ubuntu — each with its own set of Python dependencies and a system-level audio requirement. Choose the tab below that matches your operating system, or skip straight to the binary installers if you’d rather not set up a Python environment manually.
Desktop Assistant requires Python 3.9 and a working microphone. All pip dependencies listed below are pinned to versions that have been validated against Python 3.9. Using a different Python version may cause compatibility issues, particularly with PyAudio.

​
Install from Source

​
1. Clone the repository

git clone https://github.com/Harsha200105/DesktopAssistant.git
cd DesktopAssistant

​
2. Install Python dependencies

pip install -r "Requirements&COC/requirements.txt"
This installs the following packages:
PackageVersionPurpose
pygame2.0.1Music playback via pygame.mixer
SpeechRecognition3.8.1Microphone capture and Google Speech Recognition
wikipedia1.4.0Fetches two-sentence Wikipedia summaries
PyAudio0.2.11Low-level audio I/O required by SpeechRecognition
pyttsx32.90Offline text-to-speech (uses Windows SAPI5)
tk—Tkinter GUI support

​
3. Copy the configuration file

The Windows entry point requires a config.ini in the working directory you run the script from:
copy "Requirements&COC\config.ini" src\config.ini
Open src\config.ini and update at minimum the master key with your name:
[DEFAULT]
master = YourName
search_engine = Google
debug = False
musicpath =
voice = Male
rate = 150
volume = 100
energy_threshold = 300

[EMAIL]
server = smtp.gmail.com
port = 587
username =
password =

​
Binary Installers

If you prefer a pre-built package, download the installer for your platform directly:

Windows Installer (.exe)

Download the Windows setup executable. Run the installer and follow the on-screen instructions — no Python environment needed.

Ubuntu Package (.deb)

Download the Debian package. Install with sudo dpkg -i jarvis_deb.deb after downloading.

​
Troubleshooting

​
PyAudio installation fails on Windows

PyAudio depends on PortAudio, which is not bundled with the standard pip wheel on Windows. If pip install PyAudio==0.2.11 throws a build error, use a pre-compiled wheel: 
pip install pipwin
pipwin install pyaudio
Alternatively, download the matching .whl from Christoph Gohlke’s Unofficial Windows Binaries and install it directly: 
pip install PyAudio‑0.2.11‑cp39‑cp39‑win_amd64.whl

​
PyAudio installation fails on Ubuntu

Make sure portaudio19-dev is installed before running pip: 
sudo apt install portaudio19-dev python3-pyaudio
pip install PyAudio==0.2.11

​
pyttsx3 produces no audio on Ubuntu

Confirm eSpeak is installed and working: 
espeak "hello"
If you hear nothing, re-run sudo apt-get install espeak and verify your system audio output is not muted.

​
SpeechRecognition returns no results

SpeechRecognition uses the Google Speech Recognition API over the internet. Verify your network connection and check that your microphone is selected as the default input device in your OS sound settings. On Windows, you can lower the energy_threshold value in config.ini (default: 300) if the assistant isn’t picking up quieter speech. On Ubuntu, the energy threshold is hardcoded at 300 in Jarvis2.py and must be changed in the source directly.

Build docs developers (and LLMs) love

Get started for freeTalk to us