Talking-head shorts
One person talking to camera says nothing at all with the sound off. Moving captions give the viewer something to follow.
Captions for short video
Captions that move with the voice
Every word gets its own timestamp, so the active word can light up as it is spoken. Pick a style, place the captions clear of the app buttons, and render a vertical MP4 ready to post.
Related use cases
The quick answer
Open Auto Caption, drop your clip, choose the Karaoke or Bold pop style, drag the captions to where you want them, then open Export and press Render MP4.
4 steps
How to add animated captions to a clip
- 01
Open the clip
Drop an MP4, MOV or WebM up to 30 minutes. A vertical video gets short caption lines automatically, sized for a phone screen.
- 02
Whisper times every word
Only a compressed copy of the audio leaves your browser. Each word comes back with its own start and end, which is what drives the highlight.
- 03
Pick a look
Start from Karaoke, Bold pop, Boxed or Classic. Change the font, size, colors and outline, then drag the captions up or down on the preview.
- 04
Render and post
Render an MP4 with the captions burned in, then upload it to your app of choice. No watermark on the file.
Who uses it
Captions for videos people watch on mute
Tutorials and recipes
Steps stay readable on mute. Use Boxed so the text sits on a dark band and stays clear over a busy kitchen or a screen recording.
Podcast clips
Cut a strong minute from an episode, caption it in Bold pop, and post it as a teaser. Quotes land harder when each word appears as it is said.
AI narration over footage
Make a voiceover with our text to speech, lay it over your clip with Voiceover for Video, then caption the result on Auto Caption.
The auto caption generator lives on Auto Caption, our free site for animated captions. Here is what it does and how to get the most out of it.
Four caption styles to start from
The editor opens on Karaoke, but each preset is only a starting point. Change anything and it becomes your own style.
- Karaoke: white text with a dark outline, and a yellow box that jumps from word to word.
- Bold pop: big uppercase words that change color as they're spoken, placed higher on the frame.
- Boxed: text on a dark background band, with the current word colored in.
- Classic: plain outlined captions with no highlight, for when the moving effect is too much.
Under Style you can switch the highlight between Box, Color and Off, pick Space Grotesk or DM Sans, and set the size, colors, outline and background. Under Layout, drag the text on the preview or snap it to the top, middle or bottom.
Word by word captions on a vertical screen
A vertical frame is narrow, so a caption line that fits a widescreen video wraps into two or three rows on a phone. When the video is taller than it is wide, the editor splits the speech into short lines from the start. The Layout panel has Punchy, Short and Standard lengths if you want fewer or more words on screen. Changing the length re-splits every line from the word timings and replaces earlier text edits, so pick it before you start fixing typos. Undo brings everything back if you change your mind.
The free caption generator, limits included
Captioning a clip costs transcription minutes: 20 a day without an account and 60 with one, for files up to 30 minutes. A 45-second Reel uses one minute. Everything after that is free, including as many renders as you like.
The MP4 is made on your device with WebCodecs, so the video never travels to a server. Most browsers can render up to 10 minutes; Chrome and Edge on a computer reach 30. That covers short-form easily. If your phone struggles, pick Cloud in the Export panel: our GPU renders the same captions (videos up to 15 minutes, one daily minute per video minute). For long videos where you want plain subtitles rather than animated ones, the Subtitle Generator is the better fit, and Caption QA can check the exported SRT for lines that go by too fast.
Free on Auto Caption
Ready to try it on your own video?
Open the free editor on Auto Caption, drop your file, and download the result in a few minutes.
Add captions now
Opens auto-caption.app
FAQ
Auto Caption Generator FAQs
01 Is the auto caption generator free?
Yes. Captioning uses transcription minutes: 20 a day without an account, 60 a day signed in. Styling, editing and rendering the MP4 on your device are free, and the video has no watermark.
02 Does it post to TikTok or Instagram for me?
No. It gives you an MP4 file. Upload it yourself in the app the way you post any other video.
03 Is my video uploaded?
No. The video is opened and rendered by your browser. For the captions, only a compressed mono audio track is sent to the speech model.
04 Can I use word by word captions with my own SRT file?
You can import an SRT, VTT or SBV and style it the same way. Subtitle files carry one time per line, not per word, so the highlight spreads the words evenly across each line. It is close, but less exact than captions made from the audio.
05 Why did I get a WebM instead of an MP4?
Some browsers can't encode MP4 video, so the render falls back to WebM. Chrome or Edge on a computer produce MP4.
06 How long can a captioned video be?
Transcription takes files up to 30 minutes. Rendering holds the video in memory in most browsers, which caps it at 10 minutes. Chrome and Edge on a computer can save straight to disk and go up to 30. The Cloud option renders up to 15 minutes on our GPU from any device.
Still wondering? Get in touch →
Related tools
Keep going
Try it now
No voice on the clip yet?
Type the script, pick one of 54 natural voices, and download the audio. Then caption it on Auto Caption.
