Concept in development
Sayframe by Pebbora
Every word, right on cue.
Sayframe is a video tool concept that helps creators turn spoken audio into clean, readable on-screen captions. It is designed around short vertical videos where timing, emphasis and legibility matter as much as transcription.
00:089:16
Every word,right on cue.
The idea
Adding captions by hand takes time, but raw automatic subtitles rarely feel ready to publish. Sayframe explores a faster middle ground: AI-assisted transcription with simple control over timing, line breaks and a clear white caption style.
What it could help with
- 1Turn speech into timed on-screen text
- 2Shape readable line breaks for vertical video
- 3Highlight important words and moments
- 4Export a captioned video ready for publishing
A simple flow
- 01
Bring in a clip
Add a Short, Reel or another vertical talking video.
- 02
Generate the captions
AI-assisted transcription creates a timed first draft from the speech.
- 03
Refine and export
Review the wording and timing, then export captions directly on the video.
Designed for
- Short-form creators
- Small brands
- Educators and storytellers
Follow the project
Join the waitlist to hear when there is something ready to try.