Translate a video and keep the same voice
Your narrator, speaking Japanese, German or Korean
Subtitles ask the viewer to read. A stock AI voice sounds like a different person. Same-voice translation re-voices the speech in another language while keeping the voice of the person who spoke, and the translated track comes back as long as the original, so it drops straight onto the picture. We tested it on a 9-minute film in 12 languages; listen below.
Same-voice video translation opens in Doitong at the end of October.
Hear it before you try it
A 9-minute English film, translated by our team into 12 languages in the narrator's own voice. Play it and switch the language in Settings → Audio track. Listen for the same narrator in every version.
- Source
- English
- Translations
- 12
- Film length
- 9:00
- Length difference
- < 0.03 s
Who this is for
YouTube channels
One video, many audio tracks. Viewers in Tokyo and Madrid hear the same host in their own language without a second upload.
Courses and explainers
A teacher's voice is part of the lesson. Translating it keeps the person, not just the words.
Product videos and ads
Launch a demo in a new market with the presenter your customers already know.
Documentaries and stories
Narrated films, like our Pompeii test, are the easiest case: one voice, clear pauses, steady pace.
How we translated the film
The order we followed for the Pompeii film above, and the one we recommend.
Start from clean speech
Our film keeps the narration on its own track. We translated the voice alone and laid our original music and effects back under every language, so the score sounds identical in all 13 versions.
Cut long videos at pauses
The 9-minute film went in as two parts, 4:43 and 4:17, cut where the narrator stops for breath. A cut in the middle of a sentence is audible in the translation.
One language at a time
Each language is its own pass. Listen to the opening of each one before moving on.
Check names and rare words
Names and old or technical words are where translations slip. In another of our test films a character's name changed form in one language, so we now check every name by ear.
Put the track back
Each translated part came back less than 0.03 seconds shorter than the source, in every language, so the new narration lined up with the picture without retiming.
Publish
Release a separate video per language, or add every track to one YouTube video, as we did.
What changes and what stays
| Part of the video | After translation |
|---|---|
| Spoken words | Translated into the target language |
| Voice character | Kept: the same narrator, not a stock voice |
| Music and effects | Kept: we mixed the original score back under each language |
| Length | Same as the original, under 0.03 s apart |
| Picture and lip movement | Unchanged: this is audio translation, not lip sync |
The 12 languages in our test
Translated from English:
These are the languages we have tested and published. The full list will be on this page when the tool opens.
Good to know
- The mouths on screen are not redrawn. On close-ups of a talking face the mismatch shows; on narration it does not.
- Names can change form in translation. Listen to every name before you publish.
- Clean speech translates best. If your project has the voice on its own track, use it.
- Translate only videos and voices you have the rights to.
Questions about same-voice translation
Can AI translate a video and keep the original voice?
Yes. Same-voice translation re-voices the speech in another language while keeping the speaker's voice character. In our test the same narrator was recognisable across all 12 languages.
Does the translated audio match the length of the video?
In our test, yes: each part came back less than 0.03 seconds shorter than the source, in every language, so no retiming was needed.
Will the background music be lost?
Not if you keep it. We translated the narration on its own and mixed the original music and effects back under every language, so the score is identical in all versions.
Is this lip sync?
No. The voice is translated; the picture stays as it is. For narration, screen recordings and voice-over videos that is all you need.
When can I use it in Doitong?
Same-voice video translation opens in Doitong at the end of October. Create a free account now and it will be in your tools on launch day.
Keep going
Your voice, in the next language
Same-voice video translation opens in Doitong at the end of October.
Create a free account