Guide

How to turn your own clips into a video, without editing

Most people have the footage already. It is sitting in the camera roll: the walk, the coffee, the drive, the bit where you talked to the camera. What is missing isn't material, it is the hour of dragging clips onto a timeline.

The short answer

Describe the video in one or two lines and let an app find the moments. RawCut watches each clip you add once, learning what is shown second by second and what is said. After that you write something like "a day in my life" or "cinematic b-roll by the water," and it cuts a finished vertical video from your own footage.

How it works, step by step

Add clips. Pick a handful from your camera roll. Each one is analyzed once and then reused for every video you make.
Say what the video is about. One line for a theme, or one line per scene if you want a specific order.
Get the cut. The AI matches your words to the exact seconds in your clips and assembles them into a 9:16 video.
Adjust if you want. Trim, reorder, add on-screen text, or ask for another cut from the same footage.

Why not stock footage or AI-generated video?

Because it doesn't look like you. Generated clips and stock libraries produce videos that could belong to anyone, and audiences notice. RawCut only ever cuts from footage you filmed. If a line you wrote has no matching clip, it says so rather than substituting something that nearly fits.

What it is good for

Turning a shoot into several posts instead of one
Faceless or b-roll-only content
Using footage you filmed months ago and never edited
Getting a first cut in minutes rather than an evening

How many clips do you need?

Three is the minimum the app will work with, and it will say so rather than hand you an empty video. Three is enough for a short cut, but the honest answer is that variety matters more than quantity. Ten clips shot in one room give the cutter less to work with than five clips shot in five different places, because every line you write needs somewhere different to land.

A useful rule: if your script has five lines, you want at least five distinguishable settings in your library. Otherwise several lines end up competing for the same footage, and the result repeats itself.

What to write, and what not to

The single biggest factor in how good the cut is turns out to be the sentence you type. Two rules cover most of it.

Describe what can be seen, not what you feel. "Morning light on the kitchen counter" is findable. "The feeling of a fresh start" isn't, because nothing in your footage is labeled with a feeling.

Ask for footage you actually filmed. A line like "aerial shot over the coast" fails not because the app is weak, but because there is no drone footage in your camera roll. This is worth saying plainly: a script written for a stock library will disappoint, and a script written from your own life won't.

Good lines look like this:

"coffee, then the walk to the studio"
"three things I love about this street"
"the drive up, then the view at the top"

If you would rather not write at all, the app can draft a script from what is already in your library. That version never asks for footage you don't have, which is exactly why it tends to produce a fuller cut.

What happens to a line nothing matches

It is left out, and you are told. This is a deliberate choice and it is worth understanding, because most tools do the opposite. When a line has no honest match, the alternatives are to insert something that nearly fits or to admit the gap. Something that nearly fits is worse: it looks like a mistake you made, and you have to find it and remove it. A reported gap tells you exactly what to film next.

How long should the video be?

Shorter than you think. A 15-second target with five lines gives each line about three seconds, which is roughly how long a shot holds attention in a feed. Ask for 60 seconds from a small library and the cutter has to stretch: either it repeats footage or it comes back shorter than you asked. Both are honest outcomes, neither is a good video. Start at 15 or 30 seconds and lengthen only when the library can carry it.

One shoot, several videos

This is the part people discover late. The same footage answers different scripts, so one afternoon of filming isn't one post. Describe the same trip three ways and you get three genuinely different cuts, because different lines pull different seconds out of the same clips. Filming again is the expensive part; asking a second question of footage you already have costs a minute.

When the cut isn't right

Three things fix almost everything, in order of effort:

Swap one clip. Tap the shot, then Replace: clips that fit the same line are listed first, so you're choosing between real options rather than searching your whole library.
Rewrite one line. Usually the vague one. Replacing "something nice" with "the harbor at sunset" changes that segment and leaves the rest alone.
Ask for another cut. With a big enough library, another cut avoids the clips the last one used, so you get a different video rather than the same one again. You get two re-cuts per video.

What it costs, and what leaves your phone

Each clip is read once, and that reading is reused by every video you make afterwards, so you never wait for the same clip twice. Your videos aren't uploaded. To understand a clip, downscaled still frames and a compressed audio track are analyzed once, and the finished video is assembled on the device.

What it isn't

It isn't a general-purpose timeline editor, and it doesn't generate video. If you want frame-by-frame control, keyframed effects, or footage you didn't film, this is the wrong tool and a timeline editor is the right one. It also won't rescue footage that doesn't exist: it can only find what you actually shot.

A worked example: one weekend, three videos

Say you spent a weekend at the lake and came home with a camera roll full of clips: the drive, the cabin, coffee on the dock, a swim, dinner, and a few minutes of you talking to the camera about why you keep coming back.

Video one, the recap. You write "the drive up, the cabin, coffee on the dock, jumping in, dinner outside." Pick 15 seconds and you get a short recap in that order.

Video two, the mood piece. You write "quiet morning on the water." Scene lines are cut from footage without faces, so there's no talking, just mist, the dock and the light.

Video three, the talking point. You write the sentence you said on camera, roughly as you said it, and add two lines of b-roll around it. The cut lands on that sentence and keeps it whole.

Same clips, three different posts, and none of them required opening a timeline. The clips were only read once, so videos two and three take a minute or two each.

Adding your voice, text and sound

A cut from your own footage is often better with a little help on top:

Automatic captions for anything said in your clips, timed word by word, in one tap.
On-screen text for what the pictures can't say: a price, a place name, a punchline.
Mute the whole cut in one tap if you plan to add music in TikTok or Instagram, so wind and street noise don't fight the track.

When you're done, export in 9:16 and use the one-tap buttons to open TikTok or Instagram, or the share sheet for anywhere else.

Film today so tomorrow's video is easy

You don't need to plan videos to make them later, but a few filming habits make every future cut better:

Hold every shot for five seconds. Longer clips give the cutter more moments to choose from.
Film the in-between. Doors, hands, streets, the walk from A to B. These are the shots that connect a video.
Say it out loud once. If something is worth saying, say it to the camera. Speech is searchable, so it becomes material for later.
Change places. Five settings beat fifty clips from one spot.

Related guides

Questions

How do I turn my own clips into a TikTok without editing?

Use an app that reads your footage and cuts it for you. RawCut analyzes the clips already on your iPhone, then matches a short written description to the exact seconds that fit, and assembles a vertical video. You write one or two lines; you never touch a timeline.

Does it use stock footage or AI-generated video?

No. RawCut only cuts from clips you filmed yourself. It doesn't generate video and doesn't substitute stock library footage. If no clip fits a line you wrote, it tells you instead of filling the gap.

Do my videos get uploaded?

Your videos stay on your iPhone. Only downscaled still frames and a compressed audio track are analyzed, once per clip, so the app can understand what each clip contains.

How many clips do I need to make a video?

Three is the minimum RawCut will work with, but variety matters more than quantity. Five clips from five different places give the cutter more to work with than ten clips from one room. As a rule of thumb, have at least as many distinct settings as lines in your script.

Free to try. iPhone, iOS 15 or later.