AI tool · 15 credits / min

AI Caption Generator for Any Video

Upload a video and get captions timed to every word, burned in the style you pick, plus an SRT file. Translate them into another language in the same step.

Styles
6 presets
Languages
13 + auto detect
Output
MP4 + SRT
Max
10 min · 200 MB
Price
15 credits / min
Resize it for TikTok first →

What AI Caption Generator does

  • Word-level timing. ElevenLabs Scribe v2 hears each word, so captions appear exactly when they're said; music and sounds are ignored.
  • Six styles. Yellow word highlight (TikTok style), bold white, boxed, neon, karaoke fill and minimal, sized for vertical or landscape.
  • Translation. Captions can be translated into 13 languages while keeping the original timing.
  • SRT included. Download the subtitle file for YouTube, Premiere or CapCut.

How to use it

  1. Sign in and upload a video with speech.
  2. Pick a style, position and language, and a translation if you want one.
  3. Press Add captions; the captioned MP4 and the SRT download open when they're ready.

Frequently asked questions

How accurate are the captions?

Very accurate on clear speech: Scribe v2 is one of the most accurate speech models. Strong music or several people talking at once lowers accuracy.

Which languages work?

English, Turkish, Spanish, Portuguese, French, German, Italian, Arabic, Hindi, Japanese, Korean, Indonesian and Russian, or automatic detection.

How much does it cost?

15 credits per started minute of video, plus 5 credits for a translation.

Do I need an account?

Yes. Sign in with Google or email; each job costs credits from your balance, and the result is saved in My Videos.

What if it fails?

The credits are refunded automatically.

More tools