Overview Features How It Works Demo Install GitHub

Open-Source Voice Dictation for Linux

Linux Voice Dictation with Vocalinux

Open-source offline voice dictation for Linux with universal application support. Privacy-focused speech-to-text with no cloud dependencies.

Install Vocalinux Star on GitHub

Ctrl

Voice Dictation on Linux Finally Solved

The Linux Voice Gap

While macOS and Windows offer built-in voice dictation capabilities, Linux users have been left without a comprehensive, privacy-focused solution—until now.

Cloud services compromise privacy and require constant internet
Existing solutions lack system-wide integration
Poor performance with specialized Linux terminology
Complicated setup processes for casual users

The Vocalinux Solution

Vocalinux bridges this gap with a comprehensive voice dictation system built specifically for the Linux ecosystem.

100% offline processing protects your privacy
Universal application support across Linux environments
Simple, global activation with keyboard shortcut
Works with both X11 and Wayland display servers

Powerful Features

Vocalinux combines privacy, performance, and flexibility to provide a seamless voice dictation experience on Linux.

Offline & Private

Runs completely offline using Whisper models - your voice data never leaves your computer.

Universal Support

Works with all Linux applications - from terminals to browsers to office suites.

Blazing Fast

Uses optimized local models for real-time transcription with minimal latency.

Global Shortcut

Activate from anywhere with a keyboard shortcut (default: Ctrl+Alt+Shift+V).

X11 & Wayland

Compatible with both X11 and Wayland display servers out of the box.

Configurable

Choose model size, language, activation method, and other settings via config file.

How Vocalinux Works

Installation

Install Vocalinux with our simple setup script that handles dependencies and configuration automatically.

Activation

Double-tap the Ctrl key (or your custom shortcut) to start dictating in any application.

Dictation

Speak naturally, including voice commands for punctuation and formatting.

See Vocalinux in Action

Watch how Vocalinux transforms the way you interact with your Linux system.

Installation Guide

Quick Install

# Install Vocalinux
git clone https://github.com/jatinkrmalik/vocalinux.git
cd vocalinux
pip install -r requirements.txt
python cli.py install

Manual Setup

1
Install Dependencies
Ensure you have the necessary dependencies installed:
```
sudo apt install python3-pip portaudio19-dev python3-pyaudio git
```
2
Clone Repository
Clone the Vocalinux repository to your local machine:
```
git clone https://github.com/jatinkrmalik/vocalinux.git
cd vocalinux
```
3
Install Python Requirements
Install the required Python packages:
```
pip install -r requirements.txt
```
4
Install Vocalinux
Install Vocalinux on your system:
```
python cli.py install
```
5
Start Using Vocalinux
Launch Vocalinux and begin dictating with the default keyboard shortcut (Ctrl+Alt+Shift+V) or customize it in the config file.
```
python cli.py start
```

Voice Commands

Control your dictation experience with these built-in voice commands.

Text Formatting

new lineInserts a line break
new paragraphInserts two line breaks
periodInserts a period (.)
question markInserts a question mark (?)
exclamation markInserts an exclamation mark (!)
commaInserts a comma (,)
colonInserts a colon (:)
semicolonInserts a semicolon (;)
hyphenInserts a hyphen (-)

Editing Commands

backspaceDeletes the previous character
delete thatDeletes the last phrase
clear allClears all text
select allSelects all text
copyCopies selected text
pastePastes from clipboard
undoUndoes last action
redoRedoes last action
tabInserts a tab character

Customization Options

Whisper Models

Choose from different Whisper model sizes depending on your hardware and accuracy needs.

Tiny (75MB)

Base (142MB)

Small (466MB)

Medium (1.5GB)

Large (3GB)

Model Size & Language

Balance between accuracy and resource usage with different model sizes.

Small (150MB)Lower resource usage

Medium (450MB)Balanced performance

Large (1.2GB)Highest accuracy

Custom Activation

Configure your own keyboard shortcuts or even voice activation phrases.

vocalinux-config.yaml

# Vocalinux Configuration File

# Set this to 'true' if you want the app to start automatically
auto_start: false

# Default global shortcut to start/stop dictation 
# Uses the same format as the keyboard library
shortcut: 'ctrl+alt+shift+v'

# Model settings
model:
  # Options: tiny, base, small, medium, large
  size: 'tiny'
  
  # Language code (determines the model downloaded)
  language: 'en'

# Thread settings
threads: 2

# Audio settings
audio:
  # Pause detection to automatically stop recording after silence
  pause_detection: true
  # Seconds of silence to wait before stopping
  pause_threshold: 2.0
  
# Notification settings
notifications: true

Join the Community

Vocalinux is community-driven and welcomes contributors of all skill levels.

Contribute Code

Help improve Vocalinux by contributing code, fixing bugs, or adding new features through pull requests.

View GitHub Repository

Improve Documentation

Help make Vocalinux more accessible by improving documentation, writing tutorials, or creating guides.

View Documentation

Join Discussions

Participate in discussions, share your experiences, report bugs, and suggest new features.

Join Community

0 GitHub Stars

Support the Project

Star on GitHub Report Issues

Frequently Asked Questions

Is Vocalinux really 100% offline?

Yes, Vocalinux processes all voice recognition locally on your machine. Your voice data never leaves your computer, ensuring complete privacy and security.

Which Linux distributions are supported?

Vocalinux is designed to work with most major Linux distributions including Ubuntu, Fedora, Debian, Arch Linux, Linux Mint, and more. It's compatible with both X11 and Wayland display servers.

How accurate is the speech recognition?

Recognition accuracy depends on several factors including microphone quality, background noise, and the model size selected. With a good microphone and the large model, accuracy can exceed 95% for most users speaking clearly.

What are the system requirements?

Minimum requirements: 4GB RAM, dual-core CPU, and 500MB disk space for the small model. For optimal performance with the large model, we recommend 8GB RAM, a quad-core CPU, and 2GB of disk space.

Can I use Vocalinux in languages other than English?

Yes, Vocalinux supports multiple languages depending on the recognition engine selected. VOSK and Whisper engines support dozens of languages with varying levels of accuracy.

How can I customize Vocalinux for my needs?

Vocalinux can be customized through its configuration file. You can change the recognition engine, model size, activation method, keyboard shortcuts, and add custom voice commands.