AI Video Translator

Three ways to translate a video

Voice (dubbing)

A new spoken track in the target language, timed to the original. See AI dubbing.

Subtitles

Translated SRT and VTT files for YouTube, players and editors. See the subtitle generator.

Transcript

The translated text with timestamps, for reading, research and quotes.

A full translation gives you all three. Switch to text-only when you don't need a voice — it costs 1 credit per minute instead of 50.

What makes this video translator different

• Your video isn't uploaded. The browser extracts the audio, and the translated MP4 is assembled on your device — useful for unreleased, internal or personal footage.
• Long videos work: up to 2 hours per file, so full lectures, webinars and episodes don't need splitting.
• Pay per minute, no subscription: a 10-minute video with a translated voice costs 500 credits (50¢).
• Any-to-any: the spoken language is detected automatically, and any of the 21 languages can be the target.

How it works

1. Drop in a video. Your browser reads it and pulls out only the audio — the video file never leaves your device.
2. The audio is processed in 30-second chunks: speech is transcribed and the spoken language is detected automatically.
3. Each segment is translated into your chosen language.
4. The translation is read aloud in the voice you chose, and each line is fitted to the original timing — sped up by at most 1.15× with natural pitch.
5. AI vocal separation removes the original speech, and the translated voice is mixed over the remaining music and effects, which dip automatically while the new voice speaks.
6. Your browser combines the original picture with the new audio and saves an MP4.
7. Download the results. Audio and text on our servers are deleted after delivery, within 30 minutes at most.

What you get

Translated video

MP4 with your original picture and the translated voice over your original music and effects (MKV when the original video codec can't go in an MP4)

Translated audio

M4A with the same mix: translated voice over your original music and effects

Transcript

Plain text (.txt) of what was said

Timestamped transcript

Every line prefixed with its time, e.g. [12:04]

Subtitles

SRT and VTT, in the language you select

Supported files

• Video: MP4, WebM, MOV, MKV, M4V — whatever your browser can read.
• Length: up to 2 hours per file.
• Languages: speech in 21 languages is recognised automatically; translation and voices cover the same 21.

Pricing

Transcript and subtitles

1 credit per minute (0.1¢), minimum 5 credits per file

Translated voice (includes everything above)

50 credits per minute (5¢), minimum 2 minutes per file

Credits

$1 buys 1,000 credits; credits don't expire

Free credits

100 credits when you sign in with Google

Privacy

Your video is never uploaded — only its audio is, over HTTPS in small chunks. Audio, transcripts and voice files are deleted after delivery, within 30 minutes at most, and are never used to train models. Your account keeps only the file name, length, languages and credits used. Details in the privacy policy.

Good to know

• One of 8 stock voices reads the whole translation — no voice cloning and no lip-sync.
• Music and sound effects are kept by AI vocal separation, which isn't perfect: in dense mixes faint traces of the original voice can remain, and sung lyrics are removed along with the speech.
• No speaker labels — transcripts don't say who is speaking.
• Files only: no links from YouTube or social apps, and no live audio.
• Subtitles come as SRT/VTT files rather than burned into the picture.

Who reaches for a video translator

Most people arrive with one of three goals, and each points to a different run. Creators and marketers want a version of a finished video that viewers abroad will actually watch. Training, HR and support teams want the same content available at every site without re-filming it. And a large group simply received a video in a language they don't speak and want to know what it says.

That last group rarely needs a voice. Transcript mode with a target language puts the translation next to the original on the result screen for 1 credit per minute, which is a fraction of what dubbing costs. Save dub mode for videos someone will publish.

Dub mode or transcript mode, decided per video

Viewers watch with sound on, or read the target language slowly

Dub mode: a translated voice track merged with your picture, plus subtitles

Captions are normal on the platform, or several people talk over each other

Transcript mode with a target language: translated SRT and VTT files

You only need to understand what was said

Transcript mode: read the translation beside the original on the result screen

You want to edit or remix the voice yourself

Dub mode, then take the translated audio (M4A) into your editor; dub a dialogue-only export if you want the voice without the background

One difference catches people out. In dub mode, the subtitles follow what the voice actually says, including lines that were shortened to fit the original timing, so captions and voice always agree. In transcript mode the subtitles carry the full translation of each segment with no timing squeeze. If you publish a dub with captions, use the dub-mode file. The subtitles vs dubbing guide covers the audience side of this decision.

Three runs, costed

Translating into several languages means one run per language. A 20-minute training video dubbed into Spanish, French and Polish is three runs of 1,000 credits each: 3,000 credits ($3.00).

Where a machine translation slips, and how to catch it

• Names and brand terms: if speech recognition mishears a name, the translation carries the error forward. Search the transcript for every name and product before you look at anything else.
• Idioms, jokes and wordplay: these tend to come out literally. Flag them for a fluent reviewer rather than trusting the voice.
• Music and sound effects: the original speech is separated out and your background is kept under the translated voice, lowered while it speaks. In dense mixes faint traces of the original voice can remain, and sung lyrics are removed along with the speech. Background music in translated videos covers what to listen for and the optional route of dubbing a dialogue-only export and mixing the translated voice with your own music stem.
• Speakers who switch languages mid-sentence: detection works on the audio it hears, so mixed passages can come out unevenly. See videos that change language.
• Words that appear only in the picture, such as slide titles and lower thirds: mydubly translates speech, so these stay in the original language.

A broader list with workarounds is in what AI video translation can't do yet.

Where each download goes after a dub run

• Translated video (MP4, or MKV for some codecs): upload it as a separate video on platforms with one audio track per video, or embed it on a language-specific page of your site.
• Translated audio (M4A): the file to add as an extra language track where a platform supports several, or to drop into your editor for trims and fixes. It is the same mix as the MP4's audio, background included, so it can't be rebalanced on its own; for your own music levels, dub a dialogue-only export and mix the translated voice with your music stem.
• Subtitles (SRT and VTT): SRT for YouTube and most editors, VTT for players built on the HTML video element. Both follow the dubbed voice.
• Transcript: the original-language text, useful as the source for a translated description or blog post and as a reference for your reviewer.

Keep the original and every language version in one project folder with the language in each file name. When the source video changes, you'll know at a glance which versions need a new run.

Pages for your language, file or job

Each target language has its own page about what changes when a video moves into it: Arabic for right-to-left subtitles, Japanese for politeness levels and line length, Spanish for choosing between the Latin America and Spain options in the picker. For specific jobs, start from YouTube videos, training videos or webinars. Phone footage usually arrives as MOV; MOV files covers its quirks. The step-by-step translation guide walks through a first run.