Speaker tracking

Reframe horizontal video to 9:16, speaker in frame

Cropping a wide shot to vertical usually means losing the person who's talking. ClipTaro's face-aware reframing follows the speaker shot by shot, so every clip is framed like it was filmed for mobile.

60 free credits · about an hour of video · no card needed

Real clips from one podcast

88

Will AI Make Humans Obsolete?

88

The Danger of Deepfakes and How to Protect Yourself

92

Why This CEO Says Traditional Education Is Redundant

Follows whoever is talking

ClipTaro detects faces across each shot and keeps the active speaker in the frame. In two-person interviews and podcasts, the crop moves with the conversation instead of sitting in the middle of the table.

Framed shot by shot

Framing is worked out shot by shot, so the crop follows cuts in the original edit instead of drifting across them.

You have the final say

If a clip should focus on something else, adjust the focus in the editor and the preview updates instantly. You can also switch any clip to 1:1, 4:5 or 16:9.

Made for people on camera

Reframing works best where faces carry the story: podcasts, interviews, panels, keynotes, commentary and tutorials with a presenter. Multi-camera edits work too, because each shot is framed on its own.

Every clip also gets word-by-word animated captions and a title, so the reframed video is ready to post without another tool.

FAQ

Questions, answered

9:16 for Shorts, Reels and TikTok, plus 1:1, 4:5 and 16:9.

Reframing is built around faces. For screen recordings, adjust the focus manually or keep the clip in 16:9.

Yes. Speaker tracking is part of every clip on every plan.

Keep reading

Your next ten shorts are already in your videos.