Subtitles
How does speaker detection work?
Use Speaker detection on any plan, or add speakers manually, then assign, name, and style them in the editor.
3 min read
Turn it on at upload
Speaker detection is available on every plan for AI-generated uploads. In Studio, choose AI Generation and turn on Identify speakers before submitting the upload.
Speaker detection uses processing minutes like any AI transcription. It does not add a separate charge beyond the normal processing minutes for the upload.
Review speakers in the editor
When processing finishes, CutCaption splits subtitles by speaker and shows speaker chips on the caption cards.
For any project, including one uploaded without detection, use Edit > Speakers to add or rename speakers, choose colors and per-speaker styles, then use a caption's speaker button to assign it.
Show speaker names in exports
- Use the global speaker-name control to show or hide names in preview, burned-in video, and subtitle-file downloads.
- Use Edit > Speakers to hide one speaker's name or change the name-label style.
- Preview the project before exporting so speaker names, colors, and styles read clearly over the video.
Quality notes
Speaker detection can still need review. Check speaker switches, names, and short back-and-forth sections before publishing a final video or subtitle file.