Skip to main content
Dubbing translates and re-voices audio or video content into a target language. The AI handles translation, voice matching, and lip-sync timing. You can dub from a file upload or a URL.

How to dub content

1

Provide your source content

Either upload an audio or video file using the + button, or provide a URL to the content.

Dub an uploaded video into Spanish.

Dub from a URL into French.

2

Configure options (optional)

You can specify additional options in your prompt:
OptionWhat it does
Target languageThe language to dub into (required).
Source languageThe original language (auto-detected if not specified).
Number of speakersHelps the AI separate voices more accurately.
Remove background audioStrips music and ambient sound, keeping only speech for dubbing.
WatermarkUse a watermarked version for lower cost.
3

Wait for processing

Dubbing takes longer than other audio operations because the AI translates, generates new speech, and syncs timing. The agent shows progress as it works.
4

Download the dubbed content

The agent delivers the dubbed file. Video inputs produce a dubbed MP4. Audio inputs produce a dubbed MP3.
Chat showing the agent delivering a dubbed video file with download button
Use the watermarked option for drafts and reviews. It costs less. Switch to the non-watermarked version for final delivery.

What you cannot do

  • You cannot dub into multiple languages in a single operation. Run separate dubs for each target language.
  • You cannot edit the translated script before dubbing. The AI translates and voices in one step.
  • You cannot dub only a portion of the content. The entire file is processed.
  • You cannot control which voice is used for each speaker in the dubbed output.

Next steps