How-to guide

How to dub a video with AI, step by step

Dubbing a video with AI takes a few minutes of your time: the software transcribes the speech, translates it and speaks it again in a new voice. These are the steps in Dubnivo, with what to choose at each one.

Dub a video free →Free account · 10 minutes a month · no card

How it works

  1. 01

    Add your video

    Upload a video file, or paste a public link from TikTok, Instagram, Facebook, X or Twitch.

  2. 02

    Pick the languages

    Choose the language spoken in the video and the language to dub into.

  3. 03

    Download the dub

    Dubnivo transcribes, translates and re-voices the video in natural AI voices, a matching one for each speaker, then gives you an MP4 to download.

1. Start from clear speech

The dub can only be as good as the speech it starts from. Speech recorded close to the microphone, with music kept below the voice and one person talking at a time, gives the most accurate transcript and the closest voices. The preparation guide has the details.

2. Add the video

Sign in, then upload an MP4, MOV, MKV, AVI or WebM file, pick one from Google Drive, or paste a public TikTok, Instagram, Facebook, X or Twitch link. For your own YouTube videos, upload the file you downloaded from YouTube Studio. Videos can be up to 2 minutes on Free, 30 minutes on Pro and 60 minutes on Premium, Platinum or with pay-as-you-go minutes.

3. Choose the two languages

Pick the language spoken in the video yourself rather than leaving a short clip to be guessed, then the language to dub into: one of 18, from 80 spoken languages. Each extra language is its own dub.

4. Choose the voices and the sound

Each speaker gets a natural AI voice of a similar tone; with several people, each gets a separate voice. “Closest voice” keeps more of the speaker's character, “Most natural” sounds most at home in the new language. Leave “Voice only” on for the new voice alone, or turn it off to keep the music and background sound under it. You can also have subtitles written into the picture.

5. Check the translation before it is spoken

Turn on “Check the translation before dubbing”. Dubnivo stops after translating so you can correct names, numbers and wording, and the speaker of each line, before any voice is made. Fixing text now takes seconds; fixing it after the voice is made means dubbing again.

6. Download or publish

When the dub is ready, download the MP4 and the subtitles as SRT or VTT, in the new language and the original one. On paid plans you can also publish the dub to your YouTube channel or schedule it.

7. Watch once, fix and dub again

Watch the dub once before you publish it. If a line is wrong, edit it in the translation editor and dub the video again: a finished video can be dubbed again up to 3 times while its files are stored, without using more of your allowance.

Questions

Can I dub a video with AI for free?

Yes. A free account gets 10 minutes a month for dubs and AI clips, with videos of up to 2 minutes each, a small watermark and no card. Longer videos need a paid plan or pay-as-you-go minutes.

How long does AI dubbing take?

It depends on the length of the video and the queue. Paid plans are processed ahead of free videos. You can close the page; the dub keeps going and waits in your account.

Can AI dub a video with several speakers?

Yes. Dubnivo tells the speakers apart and gives each a separate voice; you can change who said a line and pick each speaker's voice in the editor. It works best when people take turns rather than talk over each other.

Will the lips match the new language?

Lip sync is not available yet: the dubbed lines are timed to the original speech, but mouth movements in the picture are not changed.