Shorts Maker: Turn Landscape Video into Vertical 9:16 with Auto Captions
Turn a video you shot in landscape into a vertical clip that's ready for YouTube Shorts, Instagram Reels, and TikTok. Choose an automatic face-following crop, a blurred-background mode that keeps the entire original frame visible, optional title text, and AI-generated captions that you can edit before exporting. Everything happens inside this browser, on your own device - nothing is uploaded to a server.
There is nothing to install and every step stays on your device: the face detector, the speech-recognition model, and the final video encoding all run using your browser's own machine-learning and recording APIs. The page can even keep working offline once it and its small AI models are cached, and your original footage is never transmitted anywhere.
Loading the tool...
When to use it
Turn a landscape interview into vertical
For footage where the speaker moves side to side, keep "Output ratio" at 9:16, choose "Follow face" under "Crop mode", then press "Analyze face position". The vertical frame follows the speaker.
Keep screen recordings and tables uncropped
When edge text must stay visible, pick "Blurred background + full frame". The original sits in the middle at a smaller size while a blurred copy fills the top and bottom.
Use only the best 30 seconds
From an hour of footage, type the moment you want into "Trim start (sec)" and "Trim end (sec)", add a headline with "Add title text", then press "Convert & save". Only the chosen part is processed.
How to use
- Drop in the video you want to convert, or click to choose a file. (MP4, MOV, WEBM · up to 3 minutes)
- Pick an output ratio (9:16, 4:5, or 1:1) and a crop mode: Follow face, Center, or Blurred background + full frame.
- Optionally enter a trim start and end time to use only part of the clip.
- If you picked "Follow face", press "Analyze face position" to scan the clip and find where faces are before rendering.
- Optionally add a title, then turn on "Auto-generate subtitles" and press "Generate subtitles" to let the AI transcribe the audio. Review the result in the editable list below - you can fix any line, or add and remove lines.
- Use the preview slider to check how the crop and captions look at different points in the clip, then press "Convert & save". Rendering happens roughly in real time relative to the clip length, so keep the tab open until it finishes.
- Download the finished vertical video, and optionally export the captions separately as a .srt file.
How it works
This tool never sends your video to a server - everything runs locally in the browser. The only downloads are the AI models: the small face-detection model (about 0.2 MB) comes from this site, and the Whisper caption model (about 77 MB for base or 250 MB for small) is downloaded once from our model storage (models.dagotools.com, with Hugging Face as a fallback). To find where to crop, an on-device face-detection AI samples the video roughly every half second, looking for the horizontal center of any face in frame. That raw position is smoothed over time (small dead-zone plus gentle exponential smoothing) so the final crop glides rather than jitters when someone moves, and the smoothed centers are interpolated between samples while rendering so the motion stays continuous frame to frame. In Blurred background mode, the source frame is scaled up and blurred to fill the entire vertical canvas, and then the full, unmodified source frame is drawn on top at a smaller size so nothing is cropped out. Captions are produced by an on-device speech-recognition model that listens to the audio track and writes out timestamped text, which is then burned directly onto the video frames during export. Rendering takes roughly as long as the clip itself, since the browser has to decode, redraw, and re-encode every frame in real time. Your file is processed in this browser and is not uploaded. To check this yourself, watch the browser's DevTools Network tab while you use the tool (step-by-step guide).
Tips for Shorts, Reels, and TikTok specs
Most Shorts, Reels, and TikTok videos default to a 1080×1920 vertical 9:16 frame. These apps typically overlay their own interface - like buttons, captions, and account info - near the top and bottom edges of the screen, so it's generally safer to keep any text you add, such as a title or caption, inside a central "safe area" rather than right at the very top or bottom. This tool places captions at roughly 72% of the frame height and titles near the top 10%, which tends to stay clear of common UI overlays, though you should always preview the result before posting since every app's layout can differ. If you're posting to the regular Instagram feed instead of Reels, a 4:5 ratio shows more of the original frame than a tight 9:16 crop; a 1:1 square works well for feed posts or square thumbnails. Exact maximum video lengths, file size caps, and other platform policies change fairly often and differ by app and by content type, so it's worth checking each platform's current help documentation before you publish, rather than relying on any single fixed number.
Choosing a crop mode
"Follow face" works well for interviews, talking-head videos, and vlogs where a person moves left and right across the frame - the crop will glide to keep them roughly centered. "Center" is a good default when the camera barely moves or when the important content always stays in the middle of the frame, and it skips the face-analysis step entirely. "Blurred background + full frame" is the right choice when you don't want to crop anything out at all - for example clips with on-screen text, tables, graphs, or multiple people who all need to stay visible - since it keeps the entire original frame inside the vertical canvas and fills the empty space above and below with a softly blurred, zoomed-in copy of the same footage.
Why automatic subtitles help
A large share of viewers watch short-form video with the sound off, especially while scrolling in public or at work, so burned-in captions can meaningfully increase how much of a video people actually watch and understand. Manually typing out every line of dialogue and timing it to match the audio is slow, so this tool automates the first draft: the speech-recognition model listens to the trimmed audio in overlapping windows and produces a list of timestamped lines, offsetting and stitching them together so the result covers the whole clip without obvious gaps or duplicated phrases. You stay in control of the final result - every line is editable, you can delete lines that aren't needed, add new ones by hand, and adjust the start and end time of any line before it gets burned into the final video or exported as a standalone .srt file.
More tips
Why vertical video needs its own version in the first place
YouTube Shorts, Instagram Reels, and TikTok are all built around a vertical video filling the entire screen by default. Upload a landscape video as-is and you get letterboxing - empty bars above and below - which makes the video look small on a phone. A vertical video that fills the whole screen uses all of that space instead.
9:16 vs. 4:5 vs. 1:1: what's actually different
9:16 is the default vertical ratio for Shorts, Reels, and TikTok, and it fills the entire vertical screen edge to edge. In most cases, this is the ratio to reach for first. 4:5 shows a wider slice of the original frame than a tight 9:16 crop, which tends to suit posts meant for the regular Instagram feed rather than the full-screen Reels tab. A 1:1 square fits feed posts or square thumbnails where you want consistent framing regardless of orientation. Which one is "best" really depends on where the video is going - the full-screen Reels/Shorts/TikTok player, or a regular scrolling feed - so it's worth picking based on the destination rather than defaulting to the same ratio every time.
Choosing a crop mode: face-follow vs. a blurred background
Once you've picked a ratio, the next decision is what part of the original frame actually gets shown. Face-follow automatically locates a person in the frame and crops the vertical window around them as they move, which works well for interviews, talking-head vlogs, and lectures where someone shifts left and right across the shot over time. If the camera barely moves and the important content always stays roughly centered, a simple center crop is often good enough and skips the extra analysis step entirely.
A blurred background that keeps the full original frame takes a completely different approach: instead of cropping anything out, it shrinks the entire landscape frame down so it fits inside the vertical canvas untouched, and fills the empty space above and below with a softly blurred, zoomed-in copy of the same footage. This is the safer choice whenever cropping would cut something important out of the shot - on-screen text, a data table or chart, a cooking demo where you need to see both the ingredients and the hands working, or a group conversation where multiple people all need to stay visible at once. If you're not sure which to pick, ask whether losing the left and right edges of the frame would lose anything that matters; if the answer is yes, lean toward the blurred-background mode instead of a crop.
Why captions matter so much for short-form video
Many people watch short-form video with the sound off - on a train, in an open office, or just scrolling in a quiet room where turning on audio would be awkward. Without captions, a viewer who can't hear the audio has essentially no way to follow what's happening, and they may scroll past quickly. Burned-in captions solve this directly: the message gets through whether or not sound is playing.
Caption placement and the UI safe zone
Vertical video apps almost always overlay their own interface elements - like, comment, and share buttons, profile info, captions the app itself adds, and navigation controls - right near the top and bottom edges of the screen. If your own captions or title text sit too close to those edges, part of the text can end up hidden behind the app's own UI. The safer approach is to keep any text you add inside a central "safe zone" rather than pinning it to the very top or very bottom of the frame. As a rough starting point, captions placed a little above the bottom third of the frame, and titles placed a bit below the very top edge, tend to clear most apps' UI overlays - though every platform's layout is a little different, so it's worth doing a quick preview inside the actual app before publishing anything important.
FAQ
Is there a length or resolution limit?
The trimmed section can be up to 3 minutes long. Anything larger than 1080p is automatically scaled down to 1080p while processing, and if the source is 720p or smaller, the output uses a smaller 720p-based vertical resolution instead.
How does "Follow face" work?
The video is sampled roughly every 0.5 seconds to find the horizontal position of any face on screen, the result is smoothed so the crop does not jump around, and the vertical frame is cropped around that smoothed center. When no face is found, it falls back to the last known position or the center.
How accurate are the AI captions?
The speech-recognition AI generates captions automatically, but accuracy can vary with accents, background noise, and specialized vocabulary. You can edit any line, or add and delete lines by hand, so always review the captions before sharing.
Which ratio should I pick: 9:16, 4:5, or 1:1?
YouTube Shorts, Instagram Reels, and TikTok mostly default to vertical 9:16. 4:5 shows a bit more of the frame and works well for the Instagram feed, while 1:1 suits square thumbnails or feed posts.
Is my video uploaded to a server?
No. Face position analysis, caption generation, and the video conversion itself all run inside this browser, on your own device, and the video file is never sent anywhere. The only downloads are the AI models: the small face-detection model comes from this site, and the Whisper caption model (about 77 MB for base or 250 MB for small) is downloaded once from our model storage, with Hugging Face as a fallback.
How big is the caption model download?
It downloads once. Under "AI model", Whisper base is about 77 MB and Whisper small about 250 MB. Small is better at Korean but slower. After that the browser reuses the saved copy.
Which languages can the captions be in?
Under "Spoken language" you can pick Korean, English or Auto detect. There is no way to pick other languages separately.
Can I add background music or transitions?
No. The tool changes the aspect ratio, trims the clip, adds a title and auto captions, and exports an .srt file. Add music or effects in another editor afterwards.
Open source used
Face position analysis runs on-device using Google's MediaPipe Face Detector (Apache-2.0 license). Automatic captions are generated with a Whisper speech-recognition model (MIT license), run directly in the browser through Transformers.js (Apache-2.0 license) and ONNX Runtime Web (MIT license). The runtime is served from this site and the models come from our own storage, with Hugging Face as a fallback; no video, audio, or face data is ever transmitted anywhere else.
⚠️ Speech recognition can make mistakes, so always check the captions before sharing. Processing takes roughly as long as the video itself and runs in real time, so please keep the tab open until it finishes. Your file never leaves your device, but please only use videos you have the rights to.
Last checked: October 8, 2026 · Dagochim team
Related tools
Video Compressor
Shrink video files for email and messaging.
Video & audioAutomatic Face Blur for Video
Find and hide faces in a video automatically with mosaic or blur.
Video & AudioMP4 to MP3 Converter
Extract the audio from a video and save it as MP3 or WAV.
Video & audioScreen Recorder
Record your computer screen with sound, no install needed.
Video & audioGIF Maker
Turn a video clip or a set of photos into an animated GIF.
Video & audio