Dubbing FAQs

How does Voice Dubbing on Kapwing work?

Originally a video and audio editing platform, Kapwing integrates multiple AI technologies to power our video dubbing product.

• Clean audio and background sounds: Kapwing extracts the spoken words of the video from other sounds, like music, laughter, and effects. This enhances the transcription and makes the dubbed audio sound more natural.
• Transcription: The dialogue of the video is extracted using speech-to-text technology and the team's glossary.
• Translation: Captions are translated using machine vendors.
• Translate Text: Kapwing uses advanced technology to scan the video, identify embedded text layers, translate them, and overlay matching text layers to ensure that embedded text is also translated to the target language.
• Synthetic voice generation: A new voiceover is created in the dubbed language. Kapwing leverages premium text-to-speech providers to make the voice sound highly realistic. For Business and Enterprise customers, the voice is cloned from the original speaker to make it as realistic as possible. Kapwing detects where the speaker changes so that it creates different voices for each speaker, improving the quality of the dubbed audio.
• Timing: The new dubbed audio is combined with the original video and background audio track in the timeline. Kapwing uses generative AI to adjust the timing of the translated audio, making it match the original video as closely as possible.
• [Optional] Lip sync: Users can turn on Lip Sync to generate a new video layer where the lips of the speaker match the new dubbed audio.

Can I dub only part of the transcript?

If you trim your original asset, only that selected portion of the asset will be dubbed. However, if you do not trim the asset down, the full asset will be dubbed.

Can I apply lip syncing to my dubbed project?

Yes! To learn how to make the dubbing match the speaker's mouth with lip syncing, be sure to check out this help center article here.

Can I preserve the original background noise?

Yes. The background audio will be automatically added to the dubbed video. You can choose to keep it or delete it from your project. You can also choose to upload a background audio track as a new layer.

What companies use Kapwing?

Kapwing’s dubbing tool is used by communications and marketing teams at multinational companies such as Chevrolet, SHEIN, OEC, Pilatesology, Hollister, and more. The tool is also used by notable universities, churches, and government agencies.

How much does dubbing on Kapwing cost?

Video Dubbing on Kapwing is free to try. To try it, create an account on Kapwing and upload a short video. Free users can upload a video less than 8 minutes long to dub a video.

Dubbing utilizes transcription, translation, and text to speech technology, so these are the limits that dubbing deducts from on Kapwing. If you dub a 10 minute, you can expect 10 minutes to be deducted from your workspace’s transcription, translation, and text to speech minutes.

To use Lip Sync for your dubbing, users can upgrade to Kapwing Pro or Business. All paid plans are billed per-seat, meaning each editor will need a license to access the platform. See our pricing page for more info.

How much does it cost to edit a dubbed video?

Once a dub is generated, any changes made to the transcription or the original language will automatically update the translation. These automatic updates will use translation minutes, based on the duration of the section that was edited.

You can update the dubbed audio by clicking “Apply changes to dubbed audio” at the bottom of the Translate tab, or “Regenerate dubbed audio” next to a specific section. When you regenerate a section, text-to-speech minutes will be used based on the length of that section.

Additional Resources:

Advanced Dubbing Tips
How to Dub a Project
How to Add Subtitles or Captions with Kapwing
How to use Text-to-Speech in Kapwing

Looking for more help?

Check our Release Notes for tutorials on how to use the latest Kapwing features!