Skip to main content
Cardboard can generate natural-sounding voiceovers from a text script using AI. Type your script, pick a voice, and the generated audio is automatically placed on your timeline — no recording equipment needed.

Generating a voiceover

1

Open the voice panel

Click the Voiceover button in the editor toolbar, or type your request directly in the AI Chat panel.
2

Write your script

Type or paste the text you want spoken. Scripts can be up to 5,000 characters long.
3

Choose a voice

Select from one of 10 preset voices. You can preview each voice before generating.
4

Adjust settings

Fine-tune stability, similarity, style, and speed to get the exact tone you want.
5

Generate

Click Generate and Cardboard creates the voiceover. The audio clip is automatically placed on the timeline at the playhead position, complete with word-level timestamps.

Choosing a voice

Cardboard includes 10 preset voices to choose from:
VoiceAccentBest for
Monika (default)AmericanNarration, explainers
DomiBritishConversational, storytelling
ElliAmericanCalm narration, meditation
MatildaAustralianFriendly, casual content

Voice settings

Fine-tune how the voice sounds with these controls:
  • Stability — Higher values produce more consistent, predictable delivery. Lower values add more expressiveness and variation.
  • Similarity — How closely the output matches the original voice model. Higher values sound more like the preset.
  • Style — Controls the stylistic intensity of the voice performance.
  • Speed — Playback speed from 0.5x (half speed) to 2x (double speed).
  • Speaker boost — Enhances clarity and presence of the voice.

Managing voiceovers

Once a voiceover is on the timeline, you can:
  • Trim it like any other clip by dragging the edges
  • Move it to a different position on the timeline
  • Adjust volume using the clip inspector
  • Add fades for smooth audio transitions
  • Regenerate with different settings if you want a different take
Generated voiceovers automatically include word-level timestamps, which means Cardboard can generate perfectly synced captions from them.
You can also use the AI Chat panel to generate voiceovers — try “Add a voiceover that says: Welcome to our product tour” or “Generate a calm female voiceover reading this script.”

What’s next?