How Translate Video dubs a video into another language
Translate Video makes a new video with speech in another language: HeyGen with lip sync or ElevenLabs with the original soundtrack. The price is per second.
Updated November 2, 20264 min read
Use Translate Video when you need the video itself in another language: a talking-head clip, a lesson, a TikTok or a YouTube video. If the text or the sound is enough, Translate Audio or translated subtitles cost much less (see Cheaper options).
What you can upload
Translate Video needs a video with a sound track. The language of the speech is detected automatically.
| Source | Where |
|---|---|
| Video from the gallery or files (Choose) | web, iOS, Android |
| Recording with the camera (Record video) | iOS and Android |
| Link (Paste link): YouTube, TikTok, Instagram, X, Facebook, Pinterest, a direct file link or another site | web, iOS, Android |
| Share menu: Translate Video in VocaLingo | iOS and Android |
Before the upload the video is compressed to about 50 MB. After compression it must be no larger than 2 GB. With HeyGen the video can be up to 30 minutes long.
How to translate a video
On the Tools tab, open Video Translation and choose the video.
Tap the settings icon (sliders) in the top right corner and choose HeyGen or ElevenLabs. The default is HeyGen.
On the Translation tab, choose the language and tap Translate video.
In Confirm the language, check the language and the price for this video, then tap Continue.
Keep the app open until the upload finishes: «Don't close the app, lock the screen, or switch apps». After «Video sent for translation» you can minimize it.
HeyGen or ElevenLabs
HeyGen changes the lips to match the new speech. ElevenLabs keeps the picture and the original music and clones each speaker.
| HeyGen | ElevenLabs | |
|---|---|---|
| Lip sync | always | optional, Lip Sync switch |
| Music and background sounds | kept, or removed with Remove background music | kept |
| Speakers | Number of speakers: Auto or 1 to 6 | detected automatically, up to 32 |
| Other options | Enhanced cloning, Enhance speech quality | none |
| Languages | about 190, with regional variants such as Portuguese (Brazil) | over 100, with regional dialects |
| Length | up to 30 minutes | no separate limit in the app |
| Best for | a person speaking to the camera | voice-over, interviews, videos with music |
Enhanced cloning makes the voice closer to the original and costs twice as much. If one person was dubbed with two voices, set Number of speakers to 1. More about voice problems is in Why the translated voice sounds robotic, and about Enhanced cloning in Video translation without lip sync and Enhanced cloning.
How long it takes and how you find out
The app gives an average of 5–15 minutes, long videos take more. The translation runs on the server, so you can close the app after the upload.
When the video is ready, you get an email and a push notification. On iPhone with app version 1.74 or later, the progress is shown in a Live Activity.
The entry appears in History (clock icon in the top right corner) with the status Queued, Processing, Completed or Failed.
If HeyGen hasn't finished within 1 hour, or 3 hours with Enhanced cloning, the job ends with an error.
What to do with a long or failed job is in Video translation, captions or transcript take too long or failed.
What you get
The result has two tabs, Original and Translation. In the app the video is saved with Share video or Save to gallery, on the web with Download video. See How to save or share a translated video.
Without Premium the video always has a VocaLingo watermark. With Premium you can turn off Add VocaLingo watermark on the Translation tab before you start.
How much it costs
Translate Video is charged per second of video and only after the result is ready. The exact price for your video is shown before you confirm.
| Mode | Per second | Per minute |
|---|---|---|
| HeyGen | 4 tokens | 240 tokens |
| HeyGen with Enhanced cloning | 8 tokens | 480 tokens |
| ElevenLabs | 4.4 tokens | 264 tokens |
| ElevenLabs with Lip Sync | 5.2 tokens | 312 tokens |
If lip sync fails, you get the dubbed video without it and pay only for dubbing: «Video translated, but lip sync failed. You were charged only for dubbing.»
Cheaper options
Under the video, the What next? block suggests cheaper ways to get the content in your language.
Add translated subtitles: makes subtitles, not a dub. The original voice stays, and Add Captions burns in subtitles in the chosen language for about 6 tokens per minute. The button is shown only before the dub is made, if the language is supported for subtitles. It starts the subtitles right away, without the language and price confirmation. If you want new speech, tap Translate video instead. The difference is explained in Add Captions or Video Translation.
Translate audio: sends the video to Translate Audio, where you get the text, the translation and a voiceover without a new video.
Add captions and Video to text are also available there.
Contact support
Describe the problem and we will reply by email. Add the file name or job ID if you have one.