Clip Utils
Go Pro

Auto Captions for Reels, Shorts & TikTok

Add bold, animated captions to a vertical video: the spoken word lights up, pops or sits on a colour box, in time with the speech. Free, no sign-up, and your video stays on your device.

Your video never leaves your device. How?

In Accurate mode only the audio is sent to our server to be transcribed, then deleted. Choose "On this device" in the settings and nothing is uploaded.

Select or drop a video or audio file

MP4, WebM, MOV, MP3, WAV, M4A, FLAC, OGG. Your video stays on your device.

Click, tap, or drop a file

16 caption styles

7 free, 9 more with ClipUtils Pro. Tap one, then choose your video.

How to add captions to a Reel

1

Choose your video

Pick the Reel, Short or TikTok from your phone or computer (MP4, MOV or WebM). Vertical, square and landscape videos all work.

2

Let the AI write the captions

Accurate mode sends only the audio to be transcribed and times every word to when it's said. Leave the language on Auto-detect, or choose it.

3

Pick a caption style

Highlight, Box, One word, Word by word, Clean, Pill and Underline, then the font, colour, size and position. The preview plays on your own video.

4

Fix any word

Tap a line to correct names, slang or brand words before you make the video.

5

Download and post

Create the video with captions and download the MP4, ready to upload to Instagram, YouTube Shorts or TikTok.

Why short videos need captions drawn in

Many people scroll Reels, Shorts and TikTok with the sound off. Without captions, they swipe past before they know what the video is about. Captions also help viewers who are deaf or hard of hearing, and people watching in their second language.

The apps' own captions give you few choices of look, and they exist only inside that one app. Captions drawn into the video stay with it wherever you post it: Reels, Shorts, TikTok, a story or WhatsApp Status. The style that holds attention is big text, two or three words at a time, with the spoken word lit up.

Mind the bottom of the screen: the apps cover roughly the lowest quarter with the post's text, the buttons and your name. The Lower position sits just above it, and Middle is safe too.

How the captions are made

Accurate mode (the default): your browser takes the audio out of the video and sends only that audio to our server, where Whisper large-v3-turbo writes the words and the moment each one is said. Nothing is kept. The video itself never leaves your device.

The captions are then drawn onto your video in your browser, in the style you picked, and saved as an MP4. Their size is set as a share of the video's height, so they look the same on a 720p or a 4K video.

3 animated videos a day are free without a watermark; after that a small cliputils.com mark is added. Classic subtitles and subtitle files never get one. ClipUtils Pro removes the mark for good and adds 9 more styles (Karaoke, Neon, Beast, Bounce, Highlighter, Typewriter, Comic 3D, Spotlight and Glitch) and 2 more fonts.

Features

16 animated styles

The spoken word lights up, pops, sits on a colour box, gets underlined or types itself out, in time with the speech. 7 styles are free; ClipUtils Pro adds 9 more.

Made for vertical video

9:16 videos get a tall preview, so you see exactly how the captions sit on a phone screen before you make the video.

Hindi and 99 languages

Whisper understands 99 languages. The Poppins and Baloo fonts show Hindi (Devanagari) correctly.

Your video stays private

Only the audio is sent to be transcribed, then deleted. Choose On this device and nothing is uploaded at all.

Edit before you make it

Fix any word, change the style and watch the preview again as often as you like.

No account

Free with fair use. 3 animated videos a day are free without a watermark; after that a small cliputils.com mark is added. Classic subtitles and subtitle files never get one.

Frequently asked questions

How do I add captions to an Instagram Reel?

Choose your video on this page and the captions are written for you, usually in seconds. Pick a style, check the preview, then download the video and post it as a Reel. The captions are part of the video, so everyone sees them, sound on or off.

Do the captions fit a vertical 9:16 video?

Yes. Vertical videos get a tall preview, and the caption size follows the video's height. The Lower position keeps the words above the part of the screen the app covers with its buttons and text.

Does it work for YouTube Shorts and TikTok too?

Yes. You get a normal MP4 with the captions drawn in, which Shorts, TikTok, Facebook, Snapchat and WhatsApp Status all accept.

Is there a watermark?

3 animated videos a day are free without a watermark; after that a small cliputils.com mark is added. Classic subtitles and subtitle files never get one. ClipUtils Pro removes the mark on every video.

Can I add captions in Hindi or other languages?

Yes, in 99 languages. Hindi speech comes out in Hindi script (Devanagari); pick the Poppins or Baloo font so it shows correctly. You can edit any line, for example to write it in English letters instead.

How long can the video be?

Accurate mode takes videos up to 15 minutes, far longer than a Reel or a Short. Longer videos are transcribed on your device instead, which is slower.

Is my video uploaded?

No. Only the audio is sent, to be transcribed and then deleted. The captions are drawn into the video on your device, and the finished video is never uploaded.

More from Auto Subtitles