Start by cloning the project repository to your local machine:
git clone https://github.com/codingsneha/Tute
cd Tute
Creating a virtual environment is recommended to manage dependencies efficiently:
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
Once the virtual environment is activated, install the necessary Python packages, including Django, pyttsx3
, and moviepy
:
pip install django pyttsx3 moviepy
Set up your database by applying the necessary migrations:
python manage.py migrate
Start the server to begin using the application:
python manage.py runserver
You can now access the project in your web browser at http://127.0.0.1:8000/.
Navigate to the upload page in the application:
- Upload your text transcript file.
- Upload the mute video file you want to process.
- Submit the files for processing.
Tute will:
- Convert the text transcript into an audio file using
pyttsx3
. - Merge the generated audio with the video file using
ffmpeg
.
After the processing is complete, you will be redirected to a success page. Here, you can view and download the final spoken tutorial.
Tute uses text to speech synthesizer **pyttsx3** to convert text to audio And the free and open-source-software **ffmpeg** to add the audio to a video file.
Back-end: Python (pyttsx3 & Django)
Front-end: html, css
The web-application is created on the Django framework.
Thank you for visiting Tute! If you encounter any issues or have suggestions for improvement, please feel free to contribute to the project or reach out. Happy creating!