Skip to content
Start free

Learn · Video & audio

How to make captions for reels and edit a video like a document

Drop your clip into aiKit's Video Kit and it writes down every word with its timing, so captions appear word by word as you speak. Pick a caption look, fix any misheard word in the Words tab, delete words to cut the video, and remove pauses and ums in one pass. Then export a vertical MP4 for reels and short videos.

About 10 minutesVideo KitVoice Kit
Video Kit's Templates for your business: grand opening, flash sale, holiday greeting and customer testimonial video templates, filtered by industry and kind
Video Kit's Templates for your business: grand opening, flash sale, holiday greeting and customer testimonial video templates, filtered by industry and kind

What you need

  • A video you shot yourself, up to 3 minutes (talk-to-camera clips, interviews and product demos work best)
  • A free aiKit account
  • Optional: your logo and brand colors in Brand Kit, so captions and text match your look

Steps

  1. Bring in your clip

    Open Video Kit and press Choose clips, pick From Graphics Library, or drop the files anywhere on the screen. Editing starts right away in your browser while the footage copies to your account in the background. The first video sets the size: 9:16 for reels and short videos.

    Video Kit →
  2. Let it write the captions

    As soon as the clip's sound is ready, the Words tab fills in on its own with every word and the moment it was said. Captions then appear a few words at a time, with the spoken word lit up. If people speak another language, set Spoken language and the words are written down again.

    Video Kit →
  3. Pick a caption look and placement

    In Captions, choose a one-click look such as Bold pop, Karaoke, Boxed or Big word. It sets the font, colors, box and how words move together, and you can change any of them after. Make key words pop highlights numbers, prices and strong selling words.

    Video Kit →
  4. Fix misheard words

    Read the Words tab once. To fix a word's spelling, double-click it (or select it and press Fix spelling), type the right word and press Enter. The sound doesn't change, only the caption.

    Video Kit →
  5. Edit the video by deleting words

    To cut a sentence, click its first word, shift-click its last word and press Delete. The video cuts those words out and shares the pause around them so the cut sounds natural. Cut words stay struck through, and Bring back puts them back.

    Video Kit →
  6. Remove pauses and ums

    Remove pauses and ums lists every long pause and every um or uh, each with a checkbox and its time. The top line says how many seconds it saves. Untick any you want to keep and press Cut. One Undo puts them all back.

    Video Kit →
  7. Ask for the finishing touches, then export

    Type any change in Ask for any change, such as make it 30 seconds, bigger yellow captions at the top, or put the price on screen when I say it, and press Make the change. Anything not done is listed first. Then press Export and choose MP4 video, which plays on phones and every major social app.

    Video Kit →

Tips

  • Many people watch short videos with the sound off, so captions carry the message. Keep each caption to a few words and make the spoken word stand out.
  • Keep captions away from the very bottom and right edge of a 9:16 frame, where app buttons and post text cover the picture.
  • Always read the captions before you post. Speech-to-text can mishear names, product names and unusual words.
  • Cut the first few seconds hard. Remove the pause and the hello so the video opens on the most interesting line.
  • Record in a quiet room with the phone close to you. Clean sound gives cleaner captions and fewer fixes.

Questions

How do I add captions to a reel automatically?
Upload the clip to Video Kit. It listens to the sound and writes down every word with the moment it was said, so the Words tab fills in by itself and captions appear in time with your voice. Choose a caption look, fix any misheard word, and export an MP4 at 9:16. Only the sound is sent to be written down; your footage stays where it is.
Can I edit a video by editing the text?
Yes. The Words tab shows everything that was said, in order. Select words and press Delete, and the video cuts those words out, keeping the timing natural around the cut. Struck-through words can be brought back at any time. It is the quickest way to trim a talking-head clip without dragging handles on a timeline.
Can I show captions in another language?
Yes. Spoken language says what language people speak in the clip, with 20 choices or Auto. Show captions in then shows the captions translated into another language, while the words you edit stay in the spoken language. You can also ask in plain words, for example put the captions in Spanish.
How long can the video be?
Video Kit makes videos up to 3 minutes, which covers reels, short videos, talk-to-camera clips and product demos. For longer edits, cut the footage into separate short videos. Finished videos are saved to your Graphics Library or downloaded as an MP4, and other export choices include WebM, GIF, a sound-only WAV and a still picture.
What if the captions get a word wrong?
Double-click the word in the Words tab, type the right spelling and press Enter. The caption changes and the sound stays the same. Captions come from speech-to-text, so names and unusual words are the most common misses. A quick read of the Words tab before you export catches them.

Terms in this guide

How businesses use it

Checked against the product on 2026-10-31.

Do it with aiKit today.

Make a free aiKit account and open Video Kit, Voice Kit and every other tool.