Caption videos right on your phone

A layout made for one thumb

On a phone the studio puts six tabs along the bottom of the screen: Words, Styles, Text, Motion, Layout and Timing. Each one opens a sheet over the preview, so the video stays visible while you change the font, pick a highlight or move the caption.

• While the video plays, it takes the whole screen, so you judge the captions the way a viewer will see them.
• With the timeline closed, the play bar carries a seek bar for jumping through the clip.
• The waveform timeline opens in the Timing tab when you want to nudge individual words.

Transcribing on a phone

You get the same two transcription choices as on a laptop. On-device transcription runs Whisper inside the browser, so the video never leaves your phone; its speed depends on the phone. Cloud transcription sends the audio to a server instead, covers 90+ languages and comes with 10 free minutes a month on a free account.

For English speech, caption breaks and missing punctuation are then filled in by a small model that also runs on the phone, so captions end at natural phrase boundaries before you touch anything.

From camera roll to finished Short

1. Open cuecaps.com/studio in Safari or Chrome and tap to choose a video.
2. Run Find words and pick on-device or cloud transcription.
3. Open Styles and try a few presets; the preview updates straight away.
4. Turn on Show Shorts safe area to see where the app's buttons sit, and keep the caption clear of them.
5. Export the MP4. A free account is needed at this step, and free exports carry a small Made with cuecaps.com mark.

The MP4 downloads like any file from the browser. On an iPhone, Safari saves downloads to the Files app, and Share, then Save Video, moves the clip into Photos for posting.

Safari versions before iOS 26 can't encode AAC or Opus audio on their own, so the studio loads a small encoder for them and the exported clip keeps its sound.

Questions