This repository uses ffmpeg and OpenAI's Whisper to automatically generate and overlay subtitles on any video.

You'll also need to install ffmpeg, which is available from most package managers:

# on Ubuntu or Debian
sudo apt update && sudo apt install ffmpeg

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

# on Windows using Chocolatey (https://chocolatey.org/)
choco install ffmpeg

After cloning the project and cd into the directory, first install the model for whisper and choose small, the default model,

if you choose a another model you will need to change too when you call the script.

npx whisper-node download

The following command will generate a subtitled/video.mp4 file contained the input video with overlayed subtitles.

node index.mjs /path/to/video.mp4 -o subtitled/

The default setting (which selects the small model) works well for transcribing English. You can optionally use a bigger model for better results (especially with other languages). The available models are tiny, tiny.en, base, base.en, small, small.en, medium, medium.en, large.

node index.mjs  /path/to/video.mp4 --model medium

Adding --task translate will translate the subtitles into English:

node index.mjs /path/to/video.mp4 --task translate

This script is open-source and licensed under the MIT License. For more details, check the LICENSE file.