A pure Python web application for transcribing audio and video files using Whisper.

• Upload audio/video files (MP3, WAV, M4A, MP4, MOV, etc.)
• Transcribe content using OpenAI's Whisper API
• Copy or download transcription results
• Clean, responsive UI
• No JavaScript dependencies - pure server-side rendering

The app supports the following audio and video formats:

• Audio: .mp3, .wav, .ogg, .m4a, .flac, .aac
• Video: .mp4, .mov, .avi, .mkv, .webm, .mpeg, .mpg

• Backend: FastAPI + Uvicorn
• Frontend: HTML + CSS (No JavaScript)
• API: OpenAI Whisper API
• Templates: Jinja2

• Python 3.11+
• OpenAI API key

1. Clone the repository:

   git clone https://github.com/yourusername/whisper-transcription-app.git
   cd whisper-transcription-app
   

2. Install dependencies:

   python3 -m pip install -r requirements.txt
   

3. Set your OpenAI API key:

   export OPENAI_API_KEY=your_api_key_here
   

4. Run the application:

   python3 -m uvicorn app:app --reload
   

5. Open your browser and go to:

   http://localhost:8000
   

You can also run the application with Docker:

docker build -t whisper-transcription-app .
docker run -p 8000:8000 -e OPENAI_API_KEY=your_api_key_here whisper-transcription-app

1. Open the application in your web browser
2. Select an audio or video file using the upload form
3. Click "Transcribe" to start the transcription process
4. Once complete, view, copy, or download the transcription result