Summarizer - Speech-to-Text Tool

A Python application that converts speech to text with background processing capability.

Features

• List all available microphone devices
• Select specific microphone device for recording
• Single speech recognition mode
• Background continuous listening mode
• Export transcripts to file
• Interactive menu interface
• Command-line interface

Installation

1. Install required dependencies:

pip install -r requirements.txt

2. Make sure you have a working microphone connected to your system.

Usage

Interactive Mode (Default)

python main.py

Command Line Options

List available audio devices:

python main.py --list-devices

Single recognition with specific device:

python main.py --single --device 1

Background mode with output file:

python main.py --background --device 1 --output transcripts.txt

Interactive Menu

The interactive mode provides a menu with the following options:

1. List audio devices - Shows all available microphone devices
2. Select audio device - Choose a specific microphone to use
3. Single recognition - Listen once and convert speech to text
4. Background mode - Continuous listening with real-time transcription
5. Exit - Quit the application

Background Mode

In background mode, the application:

• Continuously listens for speech
• Transcribes speech in real-time
• Displays timestamps with each transcription
• Optionally saves to a file
• Provides a summary when stopped (Ctrl+C)
• Offers to export all transcripts

Requirements

• Python 3.6+
• PyAudio for audio input
• SpeechRecognition for speech-to-text conversion
• Internet connection (uses Google Speech Recognition)

Troubleshooting

• PyAudio installation issues: Install portaudio first or use conda
• No microphone detected: Check system audio settings
• Speech recognition errors: Ensure stable internet connection
• Permission issues: Grant microphone access to Python/Terminal