This is a web application that transcribes audio files to text using OpenAI's Whisper model. Upload any audio file and get its text transcription.
- Simple and modern web interface
- Supports various audio file formats
- Real-time transcription status updates
- Error handling and user feedback
- Responsive design
- Python 3.8 or higher
- FFmpeg (required for audio processing)
- Install FFmpeg (if not already installed):
sudo apt update
sudo apt install ffmpeg- Create a virtual environment and activate it:
python -m venv venv
source venv/bin/activate- Install the required Python packages:
pip install -r requirements.txt- Start the Flask application:
python app.py-
Open your web browser and navigate to
http://localhost:5000 -
Upload an audio file using the drag-and-drop interface or file selector
-
Click "Transcribe Audio" and wait for the transcription to complete
- MP3
- WAV
- M4A
- OGG
- WMA
- And more...
- The maximum file size limit is set to 16MB
- Transcription time depends on the length of the audio file and your computer's processing power
- The application uses the "base" model from Whisper, which provides a good balance between accuracy and speed