Skip to main content

Subtitle Identification

The Subtitle Identification task automatically analyzes the text inside a subtitle track to accurately detect its language.

Instead of guessing based on potentially incorrect file names or missing metadata tags, this task reads the actual dialogue lines. This ensures your subtitles are correctly labeled so you can keep the languages you want, discard the ones you don't, or accurately flag tracks that need to be sent to a translation pipeline.

Configuration Settings​

Concurrent Tasks​

  • Description: The maximum number of subtitle identification tasks that can run simultaneously.
  • Usage: Because language identification relies on a lightweight, highly optimized text parsing engine rather than a heavy AI model, this can safely be left at its default value (4) or increased without impacting system performance.

Why Use Subtitle Identification?​

  • Keep Only What You Need: Easily filter your media library to keep only subtitles in your preferred languages and automatically clean up or delete unneeded tracks.
  • Accurate Language Tagging: Correctly stamps the proper 3-letter language code (like eng, spa, or ara) onto the track attributes so your media players can display them correctly.
  • Bridge to Translation: Automatically flags tracks that are not in your native language, allowing you to seamlessly route them into the Subtitle Translator workflow.