This project provides a Python-based solution to transcribe audio from video files using Google's Speech-to-Text API. It extracts audio from video files and generates transcripts in text format.
- Python 3.x
- Google Cloud Service Account Key
-
Clone the repository:
git clone https://github.com/SetuBaru/Transcriptor.git cd Transcriptor
-
Install project dependencies:
pip install -r requirements.txt
-
Set up the Google Cloud Service Account Key:
Place your
service_account_key.json
file inside the/private
directory.
-
Basic Usage:
Run the
main.py
script and follow the prompts to transcribe a video file.python main.py
-
Advanced Usage:
The
VideoTranscription.py
module provides a functionTranscribe
that can be imported and used in custom scripts or applications to transcribe video files programmatically.from VideoTranscription import Transcribe # Usage example Transcribe("path/to/your/video.mp4", "en-US")
/private
service_account_key.json
/cache
ERROR_LOGS.txt
main.py
VideoTranscription.py
ErrorHandler.py
Authenticate.py
README.md
requirements.txt
moviepy
google-cloud-speech
Contributions are welcome! If you encounter any issues or have suggestions for improvements, please open an issue or submit a pull request.
This project is licensed under the MIT License.