video-to-text Tool

The video-to-text Tool is a Python-based GUI application that allows users to transcribe audio from video files.
It utilizes Azure's Cognitive Services Speech SDK for transcription and provides a simple interface for selecting video files, entering Azure Speech Service credentials, and viewing the transcription results.

Features

• Video File Selection: Easily select the video file you want to transcribe.
• Azure Speech Service Integration: Use your Azure Speech Service subscription key and region to transcribe audio.
• Transcription with Timestamps: Get transcription results with timestamps.
• Save Settings: Save your Azure Speech Service settings for future use.

Getting Started

Prerequisites

• Python 3.6 or higher
• Azure Cognitive Services Speech subscription

Installation

1. Clone the repository to your local machine:

   git clone https://github.com/Utesgui/video-to-text.git

2. Navigate to the cloned directory:

   cd video-to-text

3. Install the required Python packages:

   pip install -r requirements.txt

Usage

1. Run the video-to-text.py script to start the application:

   python video-to-text.py

2. Use the "Select Video File" button to choose the video file you want to transcribe.

3. Enter your Azure Speech Service subscription key and region in the respective fields.

4. Click "Start" to begin the transcription process. The transcription results will appear in the log section at the bottom of the window.

5. If needed, you can save your Azure Speech Service settings by clicking "Save Settings".

Configuration

The application uses a video-to-text.ini file to store Azure Speech Service settings. This file is automatically generated and updated when you save settings through the GUI.