AI dubbing: translate your video
Dub a video or audio clip into another language with AI on PonPon — 31 target languages, how dubbing differs from voiceover, a worked example, source prep, and pairing with lip-sync.
Dubbing translates and re-voices existing audio — or a whole video — into another language. One clip can reach many markets without re-recording. PonPon dubs into 31 target languages, in the audio studio › dubbing mode.

Dubbing vs voiceover
They sound similar but solve different problems:
- Voiceover generates new spoken audio from a script you type. Use it when you're writing narration from scratch.
- Dubbing takes audio that already exists and renders it in a new language, keeping the original timing and intent. Use it when you have a finished clip and want a localized version.
If you don't have a clip yet, see Voiceover and audio basics for the full studio first.
How it works
- Open audio › dubbing.
- Upload the source — an audio file or a video with speech.
- Pick the target language (one of 31 — English, Spanish, Japanese, Korean, French, German, Portuguese, Hindi, Arabic, and more).
- Generate. PonPon transcribes, translates, and re-voices the track, then returns the dubbed result.
A worked example
You have a 20-second English product demo and want a Japanese version:
- Upload the demo clip to dubbing.
- Set the target language to Japanese.
- Generate — you get the same clip, same pacing, now in Japanese.
If the speaker is on camera, the lips will still match English; add a lip-sync pass to fix that (below).
Prep the source
Dubbing quality tracks input quality:
- Start from clean audio — minimal background noise, one speaker at a time, clear delivery.
- Avoid heavy music or overlapping voices under the speech; they confuse the translation.
- Shorter, well-separated sentences translate more naturally than long run-ons.
Dubbing and lip-sync
Dubbing replaces the sound, not the picture — so on a talking-head video the mouth still moves to the original language. To make the lips match the new audio, pair dubbing with lip-sync: see Talking avatars & lip-sync.
When to dub vs subtitle
- Dub when you want the video to feel native — ads, UGC, explainers aimed at a new region.
- Subtitle when the original voice matters (interviews, music, recognizable talent) or budget is tight.
Once dubbed, drop the clip back into the video generator flow or assemble it with the rest of your project.
Related articles
- Voiceover & audioThe PonPon audio studio: text-to-speech, voice changer, dubbing into 31 languages, sound effects, music, and multi-voice dialogue — powered by ElevenLabs and MiniMax.
- Talking avatars & lip-syncMake a character speak on PonPon: how lip-sync drives a face from an audio track with Kling 3.0, where the voice comes from, a worked example, source tips, and pairing with dubbing.
- Text-to-video basicsHow video generation works on PonPon: text-to-video vs image-to-video, choosing models like Veo 3.1, Sora 2 and Kling 3.0, and the Edit and Motion Control tabs.