We built a video editor with automatic captions + a teleprompter because making short-form videos shouldn’t require 3 different apps

#ios #mobile #showdev #startup

Hi,

My name is Andrew. For the last 6 months, we’ve been working on Captions Bro, a video editor for iPhone and iPad built specifically around creating vertical content with automatic captions.

The app is finally live on the App Store, so I wanted to share what we built and get some feedback from people who regularly create TikToks, Reels, Shorts, talking-head videos, UGC, tutorials, etc.

Problem:

Creating a relatively simple talking-head video often involves way more work than it looks like.

You record the video, import it into an editor, generate subtitles, fix the transcription, style the captions, add titles or overlays, remove awkward parts, export it, realize something is wrong, and go back again.

And if you're reading from a script, you may also need a separate teleprompter app before you even get to the editing part.

We wanted to see if we could put that entire workflow into one app without turning it into an overwhelming desktop-style editor.

Solution:

That became Captions Bro.

The basic workflow is:

Record → Caption → Edit → Export

You can record directly inside the app using the built-in teleprompter, or import an existing video from Photos.

Captions Bro then transcribes the speech directly on the device and turns it into editable captions. You can correct the transcription, change the timing, split or merge captions, and apply different caption styles.

But we didn't want to build another app that only puts subtitles over a video.

So underneath the caption workflow is an actual multi-track video editor.

You can trim, split, reorder and duplicate clips, add text/images/video overlays, use transitions, animate elements with keyframes, adjust colors, add effects and sound, and then export the finished video with the captions burned in.

The idea is that for most short-form videos, you shouldn't need to leave the app between recording yourself and publishing the finished video.

Features:

Some of the things currently included:

Automatic on-device speech transcription
Karaoke-style word highlighting
Custom caption fonts, colors, outlines and shadows
Manual caption editing, splitting, merging and retiming
Secondary-language captions
Multi-track video timeline
Trim, split, reorder and duplicate clips
Speed controls, freeze frames and transitions
Keyframe animation for position, scale, rotation and opacity
Text, image and video overlays
Masks and background removal
Color grading, filters and effects
Noise reduction, voiceovers and sound effects
Built-in teleprompter with adjustable scrolling speed
Record directly while reading your script
Export MP4 or MOV with captions burned in 9:16, 4:5 and square formats for different social platforms

One thing that was particularly important to us was keeping transcription on-device. You don't need to upload every recording to a server just to generate subtitles, and a bad internet connection doesn't stop the workflow.

We’re now trying to figure out where we should take the product next.

There are obviously already some very established apps in this space, so we're particularly interested in what creators still find annoying about their current workflow.

If you regularly create short-form video, what part takes you the most time: recording, captions, editing, or something else entirely?

Would love honest feedback.

Captions Bro is available now if anyone wants to try it.