AIDub is an AI-powered tool that automates the dubbing of videos into different languages. It processes an input video, extracts the audio, translates the transcript, synthesizes new audio in the target language, and merges it back with the original video. This solution is ideal for content creators, educators, and businesses aiming to reach a global audience.
- Automatic Speech Recognition (ASR): Extracts transcripts from video audio.
- Translation: Translates transcripts into multiple languages.
- Text-to-Speech (TTS): Generates natural-sounding audio in the target language.
- Video Merging: Combines the new audio with the original video seamlessly.
- Web Interface: User-friendly interface for uploading videos and selecting target languages.
- Python 3.7 or higher
- FFmpeg installed and added to system PATH
-
Clone the repository:
git clone https://github.com/harsh3dev/aidub.git cd aidub/backend
-
Create a virtual environment and activate it:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install the required dependencies:
pip install -r requirements.txt
-
Run the server:
python server.py
-
Access the web interface at
https://localhost:5000
(ensurecert.pem
andkey.pem
are present for SSL).
- Navigate to the live demo or run the application locally.
- Upload the video you wish to dub.
- Select the target language for dubbing.
- Initiate the dubbing process.
- Download the dubbed video once processing is complete.
This project is licensed under the MIT License.
- Harsh Pandey
- Yash Gupta
- Aditya Mondal
- Debayan Ghosh
- Soumyadeep Basak
Contributions are welcome! Please fork the repository and submit a pull request. For major changes, open an issue first to discuss potential improvements.