Automatic caption workflow · Windows

How to add captions automatically—without typing every word.

Polley Captions listens to the speech in your video, generates editable text, and gives you control over how the captions look. Follow this workflow to go from a raw video to an SRT file or a finished video with captions rendered on-screen.

Choose the video you want to caption

Start with a video that contains clear spoken audio. Open it in Polley Captions so the app can prepare the audio for transcription.

Generate captions from the speech

Run automatic transcription. Instead of manually replaying the video and typing every sentence, the spoken words become caption text you can review.

Correct the transcript

Read through names, technical terms, and punctuation. Automatic captions save the bulk of the work while the review step keeps the final result accurate.

Customize the presentation

Adjust font, size, color, and placement. Preview the captions against the actual footage so the text stays readable without covering important visuals.

Export for your editing workflow

Export an SRT file when you need a separate subtitle track, or render the captions directly onto the video when you want them permanently visible.

Choose SRT export when…

You want optional subtitles, need to import captions into another editor, or plan to upload a separate caption file to a video platform.

Render captions when…

You want the same caption design visible everywhere, including social feeds where viewers often begin watching with sound turned off.

Caption the next video in minutes.

Polley Captions is a downloadable Windows tool for automatic transcription, caption editing, styling, previewing, and export.

Buy Polley Captions on itch.io ↗