Turn Raw Footage Into a Finished Edit With 4 Prompts (Morphic Compose)
This is the exact setup from my video. You drop your raw clip into Morphic's Compose editor and type what you want. It puts the logos on screen right when you say them. Then you keep stacking. Titles. Sound effects. A follow CTA. One prompt each. Boom.
What you need
- A Morphic account
- One raw clip of you talking
- Your logo or profile picture, if you want the follow CTA at the end
Nothing to install. It all runs in your browser.
Step 1: Open Compose and drop in your clip
⚡ Open Morphic Compose
Open Morphic and go to Compose. It's the tab right next to Canvas and Copilot.
Now drag your clip in. You get a timeline like any video editor, plus a chat box on the right.
That chat box is where you type your edits.
Step 2: Tell it what to add and when
Now type what you want on screen. Say where it goes. Then say which words make it show up.
This is the first prompt from the video. I trimmed the logo list to two lines so you can see the shape. Keep adding a line for every topic in your clip.
Put three white logo cards in an arc above my head: bad on the left, good in the middle, great on the right. Show each logo blurred, then un-blur it with a quick pop the moment I say this one's bad, good or amazing. Every time I say "for" something new, swap in the next three logos.
Logos in order (bad, good, great):
For deep research: DeepSeek, ChatGPT, Perplexity
For image generation: Canva, Nano Banana, ChatGPTWhat happens when you send it
It transcribes everything you said, with timestamps. Then it generates every logo you named. Then it drops each one on the timeline at the exact word.
Before a step runs, it shows you the credit cost and waits for you to hit Generate.
Hit play. Boom, every logo pops in right when you say it.
Step 3: Add titles with one line
The logos are in. Now label them.
Send this and every card gets a tag. The tag flips to the tool's name when its logo is revealed, and the topic sits in a pill under the cards.
Now add titles for each logo and categoryStep 4: Add sound effects on every reveal
Now make every reveal hit.
Send this. It generates one reveal sound, then places it under every single reveal on the timeline.
Now add sound effects on every revealStep 5: Add your follow CTA
Last one. Attach your logo or profile picture in the chat box, then send this.
Boom. Mine came out as a follow bar with my handle at the top of the video. If yours gets the handle wrong, add your @ to the prompt.
Now add a cool follow me CTAWrite your own version
You don't need my clip for this. Use the same pattern on your own video.
Start with one big prompt. Say what goes on screen and where. Tie each thing to the words you say.
Then stack small prompts that start with Now add. One change per prompt.
Fill this in for your video:
Put [what you want on screen] [where on screen]. Show each one the moment I say "[the words you say]". Every time I say "[your cue word]", swap in the next set.
In order:
For [topic one]: [item], [item], [item]
For [topic two]: [item], [item], [item]If something lands in the wrong spot
Everything it adds sits on its own layer in the timeline. If the timing is a little off, just drag it.
If a logo comes out wrong, name the tool exactly and send the prompt again.
And keep it to one change per prompt. That's how I stacked all four.
⚡ Try it on your own clip
Get the next one first
New prompts every week.
Free. The new drops and the tools behind them, before they hit the feed.
No spam · New issues Sunday · Unsubscribe anytime
Hire me for your business
Ready to invest in a custom build?
Implementation and custom builds start at $5,000 USD. Bring a specific business problem and an approved budget. Learning on your own? Keep exploring the free guides or join the community above.
Related guides
Guide
Build a Viral Reel Decoder on Replit (My Exact Prompt)
The exact one-shot prompt I gave Replit to build an app that reverse-engineers why any reel went viral, frame by frame, with a virality score, the moves you missed, and a full breakdown.
Guide
Clone Your Voice and Add Real Emotion (Angry, Sad, Whisper on Command)
Clone your voice in under a minute, then make it whisper, rage, or break, just by typing a tag.
Guide
Make ChatGPT Write Like a Human (Beat Every AI Detector)
One instruction, saved once, and everything ChatGPT writes after it comes back reading like you, not a robot.
Frequently asked questions
No. You type what you want and Morphic puts it on the timeline for you. If you want to tweak something, drag it like you would in any editor.
In the video I added logos, titles, sound effects and a follow CTA. Each one was a single prompt on the same clip.
It transcribes your clip with timestamps first. So when your prompt says the moment I say this one's bad, it finds that exact spot and puts the edit there.
In my edit, each generation step showed its credit cost first and waited for me to hit Generate.