Rescroll

Convert horizontal video to vertical, the speaker always in frame.

Turn a 16:9 video into a 1080×1920 vertical one where the crop follows the person on screen, as an editor would, instead of a fixed slice from the middle. Free, online, no watermark, nothing uploaded.

  • 100% free
  • No watermark
  • No sign-up
  • Follows the speaker
  • Files stay on your device

Loading the tool…

It runs in your browser. Nothing is uploaded.

How it works

How to auto reframe a video, free, in three steps.

  1. 1

    Drop in your video

    A horizontal MP4, MOV or WebM: a YouTube export, a podcast recording, a webinar, a landscape phone clip. It opens in your browser; nothing is uploaded.

  2. 2

    Check the framing

    Every face is found on your device and the crop follows the speaker, shot by shot. Choose 9:16, 4:5 or 1:1, see the crop's path over your video, and drag the frame wherever you want it instead.

  3. 3

    Download the vertical MP4

    At 1080×1920 for TikTok, Reels and Shorts (or 1080×1350 and 1080×1080 for the feed), with your sound and no watermark.

Why this one

Free, with nothing held back, and nothing uploaded.

A camera that moves like a camera operator

No jitter: the frame holds still while the speaker moves within the middle 30% of it, and glides over about 1.2 seconds, easing in and out, when they move further. A cut to a new shot gets its own framing straight away.

Made for one or two people talking

One speaker stays in frame wherever they move. Two people side by side, as in a podcast or an interview, are stacked one above the other, each with their own frame, or held in one frame where they fit.

You have the last word

The crop's path is drawn over your video and on the timeline. Drag the frame at any moment and it stays where you put it until the next cut; lock it to keep one crop for the whole video.

Private, free, no watermark

Faces are found by Google's MediaPipe face detector running in your browser, and the video is made there too. Nothing is uploaded, and nothing is added to the picture.

Your file is opened and processed by your own browser. It is never sent to a server, so it stays private, and there’s no upload to wait for.

Why a moving crop beats a fixed one

A vertical crop of a horizontal video keeps less than a third of its width. If the speaker leans, walks or sits off center, a fixed crop cuts them in half or leaves them at the edge. The fix editors use is a crop that moves with them, keyframed by hand, shot by shot.

This converter does that for you. It finds the person on screen in every shot, follows them with smooth, deliberate moves, and starts each new shot with its own framing. Check it in the preview and drag the frame wherever you'd rather have it. Want the whole picture instead, with a blurred background above and below? The video resizer's horizontal to vertical converter does that.

Rescroll

Reframed. Now the rest of the edit.

Rescroll's AI video editor edits your vertical video from a sentence in a chat: “cut silences”, “remove bad takes”, “add captions”, “add nice zooms”, “add motion graphics”, made on your own footage. And to find which minutes of a long video to turn into Shorts, paste its link into Rescroll and ask: it watches the video and answers from it.

  • Silences and bad takes cut
  • Captions and zooms from one sentence
  • Ask a video for its best moments

Questions

The auto reframe tool: your questions, answered.

How do I convert a horizontal video to vertical without cutting people off?

Use a crop that follows them. Drop the video on this page: the face in each shot is found and the 9:16 crop moves with it, so the speaker stays in frame wherever they are. To keep the whole picture instead, use a blurred background, which the video resizer on this site makes.

Can AI convert a horizontal video to vertical?

Yes: that's what this page does. A face detection model runs in your browser, the crop follows the faces it finds, and the result is a vertical MP4. Nothing is uploaded to an AI service; it all happens on your device.

What does auto reframe do?

It turns a horizontal video into a vertical (or square) one by cropping, and moves the crop as the video plays so the person speaking stays in the picture. Done by hand, that's keyframing a crop for every shot; here it's worked out from where the faces are in each frame.

How does it find the speaker?

Your browser runs Google's MediaPipe face detector (its full-range BlazeFace model) over the video several times a second, and joins the faces it finds from moment to moment into tracks. In each shot, the crop follows the most prominent face: the largest and longest on screen. With two people, both are kept: one above the other, or together where they fit in one frame.

Why doesn't the frame move every time I move?

On purpose. A crop that chases every nod looks shaky. The frame waits until you've moved more than 30% of its width from the middle, then glides to you over about 1.2 seconds, starting a little before you move so you're never caught at the edge. "Quick" follows more closely; "Still" picks one place per shot and stays there.

What if it follows the wrong person or gets the framing wrong?

Pause on the moment, drag the frame where you want it, and the crop stays there from that moment until the next cut. Press Follow again to hand it back to the tracking from any later moment, or lock the crop to use one position for the whole video. The preview shows the result before anything is made.

Does it work with podcasts and interviews?

Yes. With two people side by side, the vertical video shows both, stacked: each person gets half of the frame and their own crop, which follows them. Prefer one frame? Choose One frame and it follows the more prominent person, or keeps both in shot when they sit close enough together.

How long does it take?

Usually well under the video's own length, on a recent computer. On a MacBook Pro (M4 Max) in Chrome, a one-minute 1080p talking-head video took about 6 seconds to read for faces (10 the first time on the page, while the face detector starts) and 14 seconds to make the vertical MP4. Older computers and phones take longer. Choosing a part makes it quicker: only that part is read and made.

Does it download anything?

Only the face detector, the first time: Google's MediaPipe runtime and its BlazeFace model, about 16 MB, from this site. Your browser keeps it for next time. Your video is never sent anywhere; it's read and made on your device.

Where does it struggle?

Faces it can't see: someone in profile or turned away for long, very small in a wide shot, or behind a microphone. It holds the frame where the face was last seen, so a brief look away doesn't move it. Crowds of faces and videos with no faces at all (screen recordings, B-roll) get a centered crop unless you place it. For a screen recording, a blurred background usually works better than a crop.

Is this auto reframe tool really free?

Yes. There's no price, no trial, no account and no limit on how many files you do. The auto reframe tool runs on your own device, in your browser, so it costs us nothing to run and we don't charge for it.

Does it add a watermark?

No. The file you download has no watermark, no logo and no intro or outro added. It's your file, changed only in the way you asked.

Is my video uploaded anywhere?

No. The file is opened and processed by your browser, on your device, and never sent to a server: not to us, not to anyone. You can check: watch the Network tab of your browser's developer tools while it works, and you'll see the file is never sent anywhere.

How big a file can it handle?

There's no file size limit of ours. Files of several gigabytes work, because the file is read from your disk as it's needed rather than loaded all at once. What sets the pace is your device: a long 4K video takes longer on an older laptop than on a new one.

Which browsers does it work in?

Current versions of Chrome, Edge and Safari, and Firefox on a computer: any browser with the WebCodecs API for encoding video and sound. Some files, like iPhone HEVC video, need Chrome, Edge or Safari to decode. A computer is much faster than a phone for long videos.

More free tools for your videos

Silence remover

Cut the pauses and dead air out of any video or recording, automatically. Full quality, no watermark.

Video to text

Transcribe a video or a recording in 99 languages, with timestamps and SRT or VTT captions. Nothing uploaded.

Add captions to video

Auto-captions burned into your video, word by word, in five looks, clear of TikTok, Reels and Shorts buttons. Nothing uploaded.

Filler word remover

Find every um and uh in a video or recording, check them in the transcript, and cut them out. Free, no watermark.

Video compressor

Shrink any video to a target size or quality as an MP4 that plays everywhere. No upload.

Video resizer

Change any video to 9:16, 1:1, 4:5 or 16:9 with a blurred fill or a crop. Full quality, no watermark.

Extract audio from video

Save any video's sound as MP3, WAV or M4A, the original copied untouched where possible.

Video trimmer

Cut the start and end off any video, frame-exact or lossless with no re-encoding.

Loudness normalizer

Bring any audio or video to −14, −16 or −23 LUFS, peaks held under −1 dBTP. Video untouched.

Apply LUT to video

Grade a video with your .cube LUT or a free look, see it live, and download the MP4. Nothing uploaded.

TikTok safe zone checker

See TikTok's, Reels' and Shorts' buttons and captions over your video, and download 1080×1920 PNG templates.

Blur faces in video

Every face found and followed automatically, then blurred or pixelated. Keep the ones you choose. Nothing uploaded.

Audiogram generator

A clip of your episode as a video: cover art, a moving waveform and word-by-word captions, in four shapes.

MP3 to MP4 converter

Any MP3 as an MP4 with your image on it, the whole file, ready for YouTube. Fast, even for an hour-long episode.

Bleep out swear words

Find every swear word in a video or recording, check them in the transcript, and bleep them out. Free, no watermark.

Remove background noise

Take the fan, hum, traffic and wind out from under the voice in a video or recording. Hear it before and after. Free.

Teleprompter

Read your script to camera: scrolling at your pace or your voice's, mirrored for glass, and recorded as an MP4.