Paste the caption you intended plus what the platform actually saved, and get a character-level diff that catches silently corrupted hashtags, truncation, and stripped formatting — plus a paste-safe caption block built to survive the editor that mangled it.
Paste a Reel topic and get cover-frame text, a 3-second spoken hook, and the opening shot direction — no more blank first frame.
Describe your cover frame candidates and get them judged at the size people actually see them: a self-contained HTML contact sheet at real grid and shelf dimensions, a legibility score for every text element, a ranked pick with the deciding reason, and redraw instructions for the runner-up.
Predict second-by-second viewer retention for the first six seconds of a short-form video hook, then provide concrete opening fixes.
Paste SRT subtitle text and get a cleaned SRT back — lines reflowed at natural phrase breaks, cue numbers and timestamps unchanged, plus a flagged-cue report with each fast cue's reading speed and the fix to make first.
Free rough cut for videos up to 10 minutes: puts the strongest moment at the start as a hook, removes long silences while keeping the story in order, and writes SRT subtitles. Runs offline. Upgrade to AI Story Editor Pro for bilingual subtitles, filler and retake removal, editor timelines and no length limit.
A free retention check for one published short video: paste your average percentage viewed and get a PASS / REWORK / REBUILD verdict with the threshold shown, plus the single biggest retention leak named and one concrete fix.
For a short you already posted. Send the video plus a screenshot of its retention graph (or your average % viewed) and get the curve redrawn with the drop-offs marked, the frame on screen at each drop, every leak ranked, a cut list with the new target length, and a verdict printed next to its threshold.
Put in one horizontal video and FormFit reframes it to 5 aspect ratios at once: Shorts, Reels and TikTok (9:16), Instagram feed (1:1, 4:5) and YouTube (16:9). Auto tracking prefers faces and falls back to motion to keep the subject in frame, and scenes where cropping would lose information switch to blur fill (full frame + blurred background). Logo watermark, top/bottom title bar and intro/outro cards are added in the same pipeline. Runs fully locally (uv + ffmpeg), no API key.