Skip to main content
Cardboard can automatically generate captions for any video with spoken audio. Captions are transcribed using AI, so they are fast and accurate across 20+ languages.

Generate captions

1

Open the AI Chat panel

Click the AI Chat panel on the right side of the editor if it isn’t already open.
2

Ask for captions

Type one of these prompts and press Enter:
  • “Add captions to the entire video”
  • “Generate subtitles for this clip”
  • “Transcribe and add captions”
3

Wait for processing

Cardboard will transcribe the audio and place word-by-word captions on your timeline. This usually takes a few seconds, depending on your video length.
Generated captions displayed on the video timeline

Edit captions

After captions are generated, you can edit them directly:
  • Fix text — Click on any caption on the timeline to edit the text
  • Adjust timing — Drag the edges of a caption to change when it appears and disappears
  • Delete a caption — Select it and press Delete or Backspace
  • Split captions — Break long captions into shorter segments for better readability
You can also ask the AI to make caption edits: “Fix any misspelled words in the captions” or “Break long captions into shorter lines.”

Style your captions

Cardboard includes preset caption styles that you can apply with one click. You can also customize individual style properties.

Preset styles

Choose from styles designed for different platforms and use cases:
  • Classic — White text with a semi-transparent background
  • Bold — Large, bold text with a dark outline (great for short-form social)
  • Minimal — Clean, small text at the bottom of the frame
  • Karaoke — Word-by-word highlighting that follows the audio
  • Boxed — Text inside a colored box for maximum readability

Custom styling

For each caption, you can customize:
  • Font, size, and color
  • Background color and opacity
  • Text position on the screen
  • Animation style (fade in, pop in, slide in)
Caption styles apply to all captions at once. If you change the style, every caption in your project updates to match.

Supported languages

Cardboard can transcribe and generate captions in over 20 languages, including:
  • English
  • Spanish
  • Portuguese
  • French
  • German
  • Italian
  • Dutch
  • Swedish
  • Norwegian
  • Danish
  • Polish
  • Romanian
The AI auto-detects the spoken language. You don’t need to specify it manually.

Export with captions

When you export your video, you have two options for captions:
  • Burned in (hardcoded) — Captions are permanently embedded in the video file. Viewers always see them regardless of their player settings.
  • Separate SRT file — Captions are exported as a .srt subtitle file. Viewers can toggle them on or off in supported players.
You can choose your preferred option in the export settings.

What’s next?