Capgen is an automatic captions generator for videos and audio. It employs Whisper neural network, offered by OpenAI to generate accurate timestamped captions for your videos and audio in text, srt and vtt file formats.

To observe capgen in action or play with it, open the colab notebook here

• ffmpeg for decoding all video formats.

1. Download and install ffmpeg.
2. Clone this repository by running git clone https://github.com/iangitonga/capgen.git
3. Run pip install -r requirements.txt to install Python dependencies.

• Run python capgen.py <path-to-video> to generate a captions files.
• Run python capgen.py <path-to-video> --task translate to translate captions to English.
• Run python capgen.py --help to see all the available options.