Open WhisperScribe

Open WhisperScribe is a powerful tool designed for seamless voice transcription. With its intuitive speech recognition capabilities, it transforms spoken words into written text in real-time, empowering users to enhance productivity by minimizing typing effort.

Key Features

• Natural Speech Recognition: Leverages advanced Whisper speech recognition to effortlessly convert voice to text.
• Instantaneous Transcription: Delivers real-time transcription, ready to be copied and pasted anywhere.
• Clipboard Integration: Automatically copies transcribed text to the clipboard, ensuring quick access.
• Versatile Usage: Tailored for professionals, students, creatives, and anyone seeking to optimize their typing tasks.
• Lightweight Command-Line Interface: Easy to install and operate from the command line, providing a distraction-free environment.
• Increased Efficiency: Facilitates smoother note-taking and writing processes by connecting speech directly to text.
• Background Operation: Functions quietly in the background, allowing users to continue their workflow without interruptions.

Quick Usage Guide

To use Open WhisperScribe effectively:

1. Setup: Begin by cloning the repository and executing the setup script to install dependencies.

   git clone https://github.com/nisrulz/open-whisperscribe.git
   cd open-whisperscribe
   ./setup.sh
   

2. Run the Application: Start the application, which operates in the background, permitting users to focus on other tasks:

   ./run.sh
   

3. Transcription: To initiate transcription, place the cursor in the desired text field and hold the hotkey combination (by default, Option + Shift-Left or Alt + Shift-Left) to begin recording.

4. Stop the Application: When transcription is complete or it's time to stop, simply execute:

   ./stop.sh
   

Customization Options

Open WhisperScribe allows for straightforward customization via the config.yaml file. Common adjustments include audio settings, hotkey combinations, and selecting the Whisper model to optimize performance based on user needs.

Dependencies and Credits

This project utilizes various resources, including the state-of-the-art Whisper model by OpenAI and libraries like pynput for input device management and pyperclip for clipboard functionality. For detailed information about the technologies employed, refer to the respective documentation for each dependency.

By integrating voice recognition into everyday tasks, Open WhisperScribe offers a modern solution for text input that is easy, efficient, and adaptable.