AI Dubbing for Audio and Video
Upload a short clip, check the translated transcript, then get it back in another language with each speaker's own voice and the background kept.
23 target languages
Background kept
Voices cloned
1Upload audio or video
MP3, WAV, M4A, MP4, MOV or WebM
The transcript is free. Credits are taken only when you start the dub.
2Check the translation
Each line is read in the speaker's cloned voice and fitted to the original timing. Edit any translation before you generate.
This dub costs 0 credits
Dubbing takes a few minutes: about 3.5 minutes for a 40 second clip in our tests. Keep this page open.
Your dub is ready
Your Credits
0| Credits per started minute | 6 |
| Longest clip on your plan (minutes) | 2 |
| Largest file (MB) | 100 |
Longest clip by plan (minutes): Free 2, Starter 3, Pro 5, Enterprise 5
Get more creditsWhat to expect
- Each speaker is cloned from their own lines with Chatterbox, so the dub keeps their voice in every language listed here.
- Speakers are told apart only by pauses. Two people talking back to back can come out in one voice.
- Music and background sounds are separated out and mixed back under the new voices.
- The picture is not changed: there is no lip sync. Lines are sped up or slowed down to fit the original timing.
- The transcript comes from Whisper Large v3 and the translation from translateapi.ai, so check names and terms before you generate.