How to re-voice a video into another language
Re-voice takes a video you already have and returns the same video speaking another language in the same voice. There is no script to write, no voice to record and no separate dubbing pass — you upload the clip, choose the target language, confirm you have the right to use the footage, and press Generate. This walkthrough follows the actual form, field by field.
Open the StudioNo credit card to sign up · 5 steps
Four fields, in the order the form asks for them
- 1
Open Studio and pick Re-voice
The studio is a grid of jobs rather than a list of models. Re-voice is the one described as a video going in and the same video in another language coming out. Opening it shows the form and the name of the model behind it.
studio/revoice
- 2
Upload the clip under Video
The first field is labelled Video, with the note "The video to translate — the speaker's voice is kept". Drop in the file you want dubbed. The tool reads the clip's real length out of the file you picked and prices the run on it, so you do not type a duration anywhere.
studio/revoice#video
- 3
Choose Target language
The second field is a dropdown labelled Target language. It is filled from the model's own list of supported languages, so what you see is what the model will actually accept rather than a wish list — if a language is not in the dropdown, that model does not do it.
studio/revoice#target-language
- 4
Tick the rights confirmation, then press Generate
Below the dropdown is a checkbox confirming you own the rights to the video, or have permission to use it, and that you will not upload someone else's likeness without their consent. Generate stays inert until it is ticked. The form prints the exact credit cost of the run next to the Generate button, and re-prints it whenever you change the length. Nothing is charged before you press it.
studio/revoice#rights
- 5
Collect the file from your Library
The finished vertical MP4 lands in your Library. Runs are processed in the background, so you can close the tab — the finished file turns up in your Library. We do not quote a fixed wall-clock time: it moves with the length of the run and with how busy the queue is.
library
Which dubbing model to use
HeyGen v2 Translate (Precision)
Product defaultLeave it alone unless you have a reason not to. This is the model the Re-voice tool runs on, and the precision tier is the one we point the default at.
The trade-off: It is the slower and dearer half of its family — a speed tier of the same model exists and is cheaper per second.
Specs and credit price →HeyGen v3 Lipsync (Precision)
From the model specYou do not want a translation at all — the audio is already right and only the mouth is wrong. A lip-sync model re-times the lips to a track you supply instead of generating a new language.
The trade-off: It will not translate anything. If you need another language you still need a dubbing model first, and this becomes a second run rather than a substitute.
Specs and credit price →sync-3 Lipsync
From the model specThe same job as above from a different family — worth a run when a lip-sync result comes back subtly off and you want a second opinion on the same clip.
The trade-off: Another lip-sync model, so the same limitation applies: audio in, lips re-timed, nothing translated.
Specs and credit price →These picks come from our own side-by-side runs and from what the tools actually default to. The specs and credit prices live on each model's own page and are generated from the catalogue, so they cannot drift out of date here. We do not quote anyone else's review, benchmark or price.
Your first video from $0.99
A one-time purchase — 35 credits land in your balance immediately. No subscription, nothing renews, and if a generation fails on our side the credits come back automatically.
What this does not do
- It does not write your script or change what is said. The words are the ones already in the clip, in another language.
- It does not post anywhere. We never ask for your Instagram, TikTok or YouTube password, never read your DMs and never publish anything for you. You download the file and post it yourself.
- Tools that copy movement or speech out of someone else's video ask you to tick a rights confirmation before the Generate button becomes active. Dubbing footage you do not have the right to use is not made legal by the tool asking.
- It does not fix audio that is unusable to begin with. If the speech is buried under music or clipping, the dub inherits the problem.
Common questions
Does re-voicing keep the original speaker's voice?
How long can the video be?
Why is there a rights checkbox?
What does it cost to try?
What if the result is wrong?
Keep reading
Dub your first video
Signing up and building an avatar cost nothing and need no card. You only spend credits when you press Generate.
Open the StudioNo credit card to sign up