Daily check-in: 15 free credits · Claim every day. Credits are good until 00:00 UTC, then reset.
AI Video Translator
The AI video translator turns a video of up to 10 minutes into translated SRT and VTT subtitles, burns them into the picture, or dubs the speech into a new language in the speaker's own voice. Translation uses purchased credits.
The subtitles become part of the picture, for platforms without caption files.
Pick a video to see the price.
Uses purchased credits only. Any failure refunds the full price.
Your translated video and subtitle files appear here.
How the video translator works
- 1
Upload your video
Pick an MP4 or MOV of up to 10 minutes and 5 GB. The file goes straight to our storage.
- 2
Pick the languages
Choose the spoken language or let the AI detect it, then pick one of 16 target languages.
- 3
Choose subtitles or a dub
Subtitles: the speech is transcribed and translated. Dub: the voices speak the new language, and the music stays.
- 4
Download the result
Watch it on the page and download the MP4, the SRT or the VTT file. Every translation is saved in My Works.
What people translate
YouTube videos for new markets
Upload SRT captions in a second language, or publish a dubbed version for viewers who do not read subtitles.
Short videos with burned-in captions
TikTok, Reels and Shorts are often watched without sound. Burned-in subtitles make every view count.
Courses and tutorials
Translate a lesson once and reach students in Spanish, Portuguese, Hindi or Japanese without new recordings.
Product demos and ads
Dub a product walkthrough so customers hear it in their own language, with the same presenter's voice.
More video tools
A Guide to Translating Videos with AI
Subtitles or a Dub: Which One You Need
Translated subtitles keep the original voices and add text in the new language. They are the cheapest way to reach a new audience, and platforms such as YouTube accept the SRT file as a separate caption track, so viewers can turn it on or off.
A dub replaces the speech itself. The AI separates the voices from the music and background sound, translates what each speaker says and speaks it again with a voice cloned from the original speaker. Viewers who do not like to read subtitles, children and people who watch on a small screen usually prefer a dub.
How the Subtitles Are Made
First a speech recognition model writes down every word with its exact start and end time. The words are grouped into short cues of at most six seconds and two lines, broken at the end of a sentence or at a pause, so each cue is easy to read.
Then Claude translates the cues in order, one line for each cue. The timing of every cue stays the same as in the original speech, so the translated subtitles appear exactly when the words are spoken. You get the result as an SRT file and as a WebVTT file.
When to Burn Subtitles into the Video
Burned-in subtitles are part of the picture. They show on every platform and every player, also where caption files are not supported, such as many short video apps and messaging apps.
Keep the subtitle files when the platform supports them. A separate caption track can be switched off, is read by search engines, and can be replaced later without a new export. You can also do both: burn the subtitles in and keep the SRT for YouTube. The YouTube Clip Maker can then cut short clips from the translated video.
Tips for a Better Translation
Clear speech gives the best result. Loud music under the voice, many people who talk at the same time, or a strong echo can cause errors in the transcription, and every error carries into the translation.
Set the spoken language yourself if the video mixes languages or starts with music. Automatic detection listens to the first part of the speech. For a dub, a recording with one or two clear speakers gives the most natural cloned voices.
What It Costs
Translated subtitles cost about 1 credit for a 1-minute video and 5 credits for a 10-minute video; burning them into the picture raises a 10-minute video to about 7 credits. An AI dub costs about 220 credits per minute of video, because every voice is cloned and generated again. The page shows the exact price before you start.
The translator uses purchased credits only. If any step fails, the full price returns to your balance. See pricing for the credit packs.