Guide
Text-based editing means you change the transcript; conversational editing means you ask
Updated
Text-based video editing means you edit the transcript and the video follows. Conversational video editing means you tell an AI editor what to change in a chat, and it makes the change for you.
In short
- Text-based video editing means you edit the words of the transcript, and the video is cut to match. Conversational editing means you type a request and an AI makes the change.
- Text-based editing is fastest for small, exact fixes, like cutting one um or fixing one misheard caption word.
- Conversational editing is better for changes that need a search or a judgement, like finding b-roll or making the whole video shorter.
- Some editors have both. Descript, Kapwing and Cutroom's Magic Editor each pair a transcript with an AI you can ask.
- In Cutroom's Magic Editor, tapping words in the transcript is free, and a chat message that changes the video costs 40 credits.
What is the difference between conversational and text-based editing?
Both methods skip the timeline. The difference is who makes the change: you, by editing the words, or an AI, from what you ask.
Text-based and conversational editing side by side
Examples as each company describes its own product, November 2026.
What you do
- Text-based editing
- Edit the transcript, word by word
- Conversational editing
- Type what you want in a chat
Who makes the change
- Text-based editing
- You, by hand
- Conversational editing
- The AI, from your request
Fastest for
- Text-based editing
- One exact word or sentence
- Conversational editing
- Changes across the whole video
Weak at
- Text-based editing
- Anything that isn't a word, like b-roll
- Conversational editing
- Tiny fixes, and you check what it did
Examples
- Text-based editing
- Descript, VEED, Kapwing's transcript trim
- Conversational editing
- Descript's Underlord, Kapwing's Kai, Cutroom's Jacob
| Text-based editing | Conversational editing | |
|---|---|---|
| What you do | Edit the transcript, word by word | Type what you want in a chat |
| Who makes the change | You, by hand | The AI, from your request |
| Fastest for | One exact word or sentence | Changes across the whole video |
| Weak at | Anything that isn't a word, like b-roll | Tiny fixes, and you check what it did |
| Examples | Descript, VEED, Kapwing's transcript trim | Descript's Underlord, Kapwing's Kai, Cutroom's Jacob |
What text-based editing is fastest at
Text-based editing turns the video into a document. You delete a word, and the video loses that word too. It can't help with what isn't a word, like b-roll or music.
In Cutroom's Magic Editor, you tap a word to cut it, bring it back or fix its caption. Taps are free and happen right away.
- Cutting one um, a cough or a false start is a matter of selecting the word and deleting it.
- Fixing a misheard caption word, like a name or a price, is a quick retype in the transcript.
- Removing every filler word at once takes one click in VEED or Descript.
- Moving a sentence is a copy and paste in VEED's transcript, which Cutroom's Magic Editor can't do.
How Cutroom's Magic Editor edits a video like this
Jacob is the AI editor inside Cutroom's Magic Editor: it edits your video for you, then changes it when you ask in a chat.
The 4 styles, as example edits
Steps
Three steps, four angles
Skit
Hook, hard stop, demo card
Verdict
The tester's verdict
Poster
Typography does the talking
Hover or tap an example to play it, without sound. These are example edits of each style; the presenters in them are generated with AI.
- Your take: one video of you talking, up to 3 minutes
- Your style: one of 4: Steps, Skit, Verdict or Poster
- Your files: screenshots, a screen recording or a logo, if you have them
- Your goal: what the video is for, in a few words, if you like
- Jacob makes it: normally 10 to 15 minutes, and you get an email
- Your edit: ask Jacob for changes in a chat, then export
Then you ask Jacob, for example
- “Make this about 10 seconds shorter”
- “Put a clip on the strongest sentence”
- “Change the music to something calmer”
Each change is a new version, and going back is free. First cut 250 credits, each change 40, questions free, export 30 credits per started minute.
What conversational editing can do that text cannot
Conversational editing hands the judgement to the AI. You ask for a result, like a shorter video, and it decides which words and clips to change.
In Cutroom's Magic Editor, Jacob makes the whole first edit from one press of "Make my video". After that, each chat message that changes the video costs 40 credits, and questions are free.
- You can ask "Can you find 3 b-roll clips that fit what I'm saying?" and Jacob looks in your own clip library first, then on Pexels and Pixabay.
- You can ask "Make this about 10 seconds shorter" and Jacob cuts the weakest parts, keeping the opening and the ending.
- You can ask "Switch this to the Poster style" and Jacob rebuilds the edit in that style for 120 credits.
- You can ask "Why did you cut what you cut?" and get an answer from a log of the edit, for free.
A trainer's pricing clip, before and after
In this example, Jacob makes the first edit from one press. You then type the two requests below in the chat.
Drawing of an example clip, not a customer video
Before · the clip as filmed
A 40-second phone video of a personal trainer explaining her online plan
“The, uh, the plan costs nine dollars a month. You get three workouts a week, um, … (pause) and a check-in with me every Sunday.”
struck through = what Jacob cuts
After · Jacob's first edit, Steps style
“The plan costs nine dollars a month. You get three workouts a week, and a check-in with me every Sunday.”
- On “plan”: your screenshot plan.png in a floating window
- On “dollars”: the word set big under the window
- On “check-in”: your screenshot checkin.png in the window
- On “Sunday”: you full screen, with your logo as a sticker
- Under the whole video: calm music under your voice
window: plan.png
Then you ask Jacob
- “Put a clip on the strongest sentence”v2a stock clip of a home workout on the words three workouts a week
- “Make the key words stand out more”v3the key words, like nine dollars, stand out more in your accent colour
Which editing method to use, change by change
You don't have to pick one. Use the transcript for small, exact fixes, and ask the AI when a change needs a search or a judgement.
In the Magic Editor, word taps and the chat with Jacob are on the same screen. Use the free tap when it does the job.
Tap the transcript or ask Jacob: which to use for each change
Prices in Cutroom credits. Questions to Jacob are free, up to 20 a day.
| The change you want | Tap the transcript | Ask Jacob in the chat |
|---|---|---|
| Cut one um or a repeat | Tap it and cut it, free | Works too, for 40 credits |
| Fix a misheard caption word | Tap it, then Fix this word, free | Works too, for 40 credits |
| Put your screenshot on a sentence | Tap the words and add your file, free | Works too, for 40 credits |
| Find b-roll for the strongest line | Not by tapping | "Put a clip on the strongest sentence", 40 credits |
| Make it about 10 seconds shorter | Cut sentence by sentence yourself | "Make this about 10 seconds shorter", 40 credits |
| Know why a part was cut | Not by tapping | "Why did you cut what you cut?", free |
The change you want: Cut one um or a repeat
- Tap the transcript
- Tap it and cut it, free
- Ask Jacob in the chat
- Works too, for 40 credits
The change you want: Fix a misheard caption word
- Tap the transcript
- Tap it, then Fix this word, free
- Ask Jacob in the chat
- Works too, for 40 credits
The change you want: Put your screenshot on a sentence
- Tap the transcript
- Tap the words and add your file, free
- Ask Jacob in the chat
- Works too, for 40 credits
The change you want: Find b-roll for the strongest line
- Tap the transcript
- Not by tapping
- Ask Jacob in the chat
- "Put a clip on the strongest sentence", 40 credits
The change you want: Make it about 10 seconds shorter
- Tap the transcript
- Cut sentence by sentence yourself
- Ask Jacob in the chat
- "Make this about 10 seconds shorter", 40 credits
The change you want: Know why a part was cut
- Tap the transcript
- Not by tapping
- Ask Jacob in the chat
- "Why did you cut what you cut?", free
Questions people ask
- What is conversational video editing?
- Conversational video editing means you change a video by telling an AI editor what you want in a chat, like "Make this about 10 seconds shorter". The AI makes the change, and you check the new version.
- What is text-based video editing?
- Text-based video editing shows the video as a transcript, and you edit the words. Delete a word and the video is cut to match. Descript and VEED are well-known examples.
- Which is faster, text-based or conversational editing?
- Text-based editing is faster for one exact fix, like a single um or a misheard word. Conversational editing is faster for changes across the whole video, like making it shorter or finding b-roll.
- Can I use both methods in one editor?
- Yes. Descript pairs its transcript editing with Underlord, Kapwing offers both Kai and transcript editing, and Cutroom's Magic Editor has free word taps beside the chat with Jacob.
- Does conversational editing cost more in Cutroom?
- Yes, a little. Tapping words is free, and a chat message that changes the video costs 40 credits. A question that changes nothing is free, up to 20 a day.
- Can Cutroom move a sentence to another place?
- No. The Magic Editor can cut and restore words, but it keeps your sentences in the order you said them. A text-based editor such as VEED lets you move parts of the transcript.
Want to try both ways on one clip? Upload it, let Jacob make the first edit, then tap or ask. Your first video is free.