Video translation without lip sync, audio only and Enhanced cloning

Translate Video always makes a new video and charges for every second of it. If you need less than a full dub with lip sync, one of the options below is cheaper or closer to what you want.

Which option to choose

The table compares the result and the price per minute of video.

The Translate Audio price depends on the length of the translated text. Exact prices are in Token pricing for each tool.

How to translate only the speech of a video

Translate Video no longer has an Audio only switch. Translate Audio does this job: it accepts the video itself, takes the sound from it and gives you the text, the translation and a voiceover.

1. On the Tools tab, open Audio Translation.

2. Tap Choose and select the video file, or tap Paste link. You don't need to extract the sound first.

3. Wait for recognition and translation, they start by themselves. On older phones taking the sound out of a long video can take a while, keep the screen open.

4. On the Translation tab, check the language and tap play to hear the voiceover.

5. Tap the share button in the player to send or save the audio file. On the web it downloads the file.

If the video is already open in Translate Video, tap Translate audio in the What next? block to send it to Translate Audio. A file from your device must be up to 100 MB; by link it can be up to 2 GB. More in How Translate Audio works.

How to get a dubbed video without lip sync

Choose ElevenLabs in Translate Video. It replaces the speech, keeps the picture, music and sound effects, and clones each speaker.

1. Open Video Translation and choose the video.

2. Tap the settings icon (sliders) in the top right corner and choose ElevenLabs.

3. Leave the Lip Sync switch off.

4. Choose the language, tap Translate video and confirm.

What Enhanced cloning does

Enhanced cloning is a HeyGen option. The app describes it as «Higher quality translation with dynamic duration. The cost is 2x higher.» In practice it gives a dubbed voice closer to the original speaker.

It is worth it when people know the speaker's voice: interviews, personal videos, a blogger on camera. For a short clip or a voice behind the scenes, plain HeyGen or ElevenLabs is usually enough.

To turn it on, open the settings in Translate Video, choose HeyGen and switch on Enhanced cloning. The price per second next to the Translate video button doubles right away. A HeyGen job with Enhanced cloning can take longer: VocaLingo waits for it up to 3 hours.

Frequently asked questions