Takes Edit videos with Claude Code

How to edit videos with Claude Code.

Claude Code can edit your videos. Whisper writes down every word, ffmpeg cuts out the pauses and ums, and Claude checks the frames and writes the posts. Set it up by hand with a skill, or let Takes for Mac do it with one line.

Do it by hand

Free and open source · macOS 15+ · runs on your Claude plan

Claude Codeediting take-01-camera.mov
  1. Read the take3:18 · camera
  2. Write down every wordWhisper
  3. Find the pauses36 pauses · 1:57
  4. Cut in the silenceffmpeg · 3:18 → 1:24
  5. Check the frames4 stills · all clear
  6. Write the postsLinkedIn · X · Shorts

The short answer

Three things to know first.

Claude does not watch the video

It reads what you said, word by word, and looks at still frames. That is enough to cut a talking-head video well.

Free tools do the work

Whisper turns speech into text. ffmpeg cuts and crops. Both are free and run on your computer.

You give notes in plain words

"Cut the stutter at 0:14." Claude makes a new version. You never touch a timeline.

Skill, code or plugin

Three ways Claude edits video.

People mean one of these when they say "Claude Code video editing." This guide is the first one: it is the fastest way to a rough cut of a talking-head video.

This guide

Cut your files with a skill

Claude Code runs ffmpeg and Whisper on your video. A skill tells it the steps. Best for silences, ums, 9:16 and captions.

Write the video as code

Remotion or HyperFrames turn code into video. Best for motion graphics and explainers, not for cutting a long take.

Drive an editor

A plugin or MCP server connects Claude to Premiere Pro or DaVinci Resolve. You keep the timeline, Claude makes the changes.

A real video

One video, from raw take to post.

Marvin made this LinkedIn video on October 1, 2026. Claude Code did every cut. Here is what happened, with the real numbers.

14 seconds of the finished video. The note on the frame says "make me look young again".
3:18raw take
36pauses found
1:24first cut
27notes from Marvin
9versions
1:10posted
The take, to scale3:181:24
TalkingPause (36 of them, 1:57 in all)
Notes per versionMarvin's comments on each edit
1v2
12v3
6v4
2v5
3v6
1v7
1v8
✓v9

The first full draft got the most notes. After that, they drop fast. Version 9 went out.

Some of the real notes

  • v3 · 0:14"I stutter here a little, any chance you can correct?"
  • v3"Mic overdrive noise, can you remove it?"
  • v3"Audio is a little out of sync."
  • v4"Too many stuttery pauses, please cut."

Each note sits on a time and an area of the frame, so "here" and "this" are clear. Claude fixed each one in a new version.

Step by step

What Claude Code does, in six steps.

The same steps, by hand or in Takes. The commands are further down.

1Write down every word

Whisper turns your voice into text, with the second each word starts. These are the real first words.

2Find the pauses, ums and restarts

ffmpeg lists every silence. Claude reads the words and spots a line you said twice. It keeps your last clean try.

3Cut inside the silence

Each cut lands in the middle of a pause, with a tiny fade. No word gets clipped, and there is no click.

4Make it vertical

For Shorts, Reels and TikTok, ffmpeg crops a 9:16 frame around your face, not the middle of the picture.

5Add captions

From the word times of the final cut. Short lines, low on the screen, clear of your face.

6Check the frames

A command that ran proves nothing about how it looks. Claude saves stills from the result and looks at each one.

Then the posts

The same chat writes the posts.

Claude reads the transcript of the final cut and writes one post for each platform. In Takes you see each one the way it will look.

Takes · Post
The Post tab in Takes: a LinkedIn post with the video, as LinkedIn shows it The Post tab in Takes: the vertical short with its caption, as TikTok shows it The Post tab in Takes: an X thread with the video The Post tab in Takes: the YouTube title, description and thumbnail

Two ways

By hand, or with Takes.

Both use Claude Code, ffmpeg and Whisper. The difference is how much you set up and where you give notes.

By handWith Takes
Set up the toolsInstall ffmpeg, Whisper and Claude Code yourselfOne line installs all three
Teach Claude how to editWrite your own instructions, or find a video editing skill on GitHubShips the takes-video-edit skill with tested ffmpeg commands, plus the takes MCP server
Record the videoAnother app (QuickTime, OBS, your phone)Built in, with a teleprompter
Give notesType times into the terminal: "at 0:14…"Click the frame, mark the area, type the note
See the postsPlain text in the terminalPreviews for LinkedIn, X, YouTube and Shorts
Runs onMac, Windows, LinuxMac with Apple silicon, macOS 15+
CostFree tools + your Claude plan or API creditsFree app + your Claude Pro or Max plan

Guide

Do it by hand, in five steps.

For one video in a folder. Claude Code runs the commands for you. They are here so you know what it does.

Install the tools

On a Mac with Homebrew:

brew install ffmpeg
pip install openai-whisper
curl -fsSL https://claude.ai/install.sh | bash

The last line installs Claude Code. Sign in with your Claude account the first time you run claude.

Ask for the edit

Open Terminal in the folder with your video, run claude, and ask in plain words:

Edit take.mov into a tight cut. Use Whisper for word times
and ffmpeg to cut. Cut every pause over 0.4 s, the ums and
any line I said twice (keep the last try). Cut only inside
silence, with a 15 ms fade. Save it as edit-v1.mp4, then
save 4 stills and look at them before you say it is done.

The more exact the ask, the better the first cut. Put rules you always want in a CLAUDE.md file in the folder, so Claude reads them every time.

The commands it runs

Words with times. The prompt full of fillers makes Whisper keep the ums, so they can be cut:

whisper take.wav --model small.en --word_timestamps True \
  --output_format json \
  --initial_prompt "Umm, let me think like, hmm... Okay, uh, here's what I'm, like, thinking."

Find the silences:

ffmpeg -i take.wav -af silencedetect=noise=-40dB:d=0.12 -f null - 2>&1 | grep silence_

Cut and join. One filter keeps picture and sound in sync. Each piece is a start and end time from the steps above:

ffmpeg -i take.mov -filter_complex "
[0:v]trim=1.20:4.85,setpts=PTS-STARTPTS[v0];
[0:a]atrim=1.20:4.85,asetpts=PTS-STARTPTS,afade=t=in:d=0.015[a0];
[0:v]trim=5.40:9.10,setpts=PTS-STARTPTS[v1];
[0:a]atrim=5.40:9.10,asetpts=PTS-STARTPTS,afade=t=in:d=0.015[a1];
[v0][a0][v1][a1]concat=n=2:v=1:a=1[v][a]" -map "[v]" -map "[a]" edit-v1.mp4

Vertical 9:16, where X is the left edge of the crop, centred on your face:

ffmpeg -i edit-v1.mp4 -vf "crop=ih*9/16:ih:X:0,scale=1080:1920" vertical-v1.mp4

Captions from an .srt file that Claude writes from the word times of the final cut:

ffmpeg -i vertical-v1.mp4 -vf "subtitles=captions.srt" vertical-captions-v1.mp4

Check and give notes

Claude Code cannot play the video, so it checks still frames:

ffmpeg -ss 12.5 -i vertical-v1.mp4 -frames:v 1 check-12.png

Then you watch it. Give notes with a time: "At 0:14 I stutter, cut it." Ask for a new file each time (edit-v2.mp4), so you never lose a version that was good.

This is the slow part by hand: you write times and describe the frame in words. In Takes you click the frame and mark the area instead, and the note goes to Claude with a picture of it.

Ask for the posts

Transcribe edit-v2.mp4 and write a LinkedIn post, an X post
and a Shorts caption from it. Hook in the first line,
no hashtags, sound like me.

Claude writes from what you actually said in the final cut, not from the script, so the post matches the video.

Good to know

Where it shines, and where it doesn't.

Works well for…

  • talking-head videos: one person, talking to the camera
  • a rough cut: no dead air, no restarts
  • cutting pauses, ums and false starts
  • vertical clips and captions from one long take
  • posts that match what you said

Watch out for…

  • names and rare wordsWhisper can mishear them. Read the captions before you post.
  • fast action and b-roll timingClaude sees stills, not motion. Check those parts yourself.
  • effects, transitions, templatesA timeline editor like CapCut or Final Cut is made for that.
  • made-up ffmpeg flagsLong filter chains can fail. A skill with tested commands fixes most of it.
  • many rounds on the Pro planCutting runs on your computer. Many notes in one day can still reach the limit.

The easy way

Skip the setup. One line in Terminal.

It installs Takes, ffmpeg and Claude Code, signs you in and opens the app. Run it again to update.

NeedsApple silicon, macOS 15+, and a paid Claude plan (Pro or Max) for the AI parts.
Rather click?Download the .dmg, then click Finish setup in the sidebar.
Free and openMIT licensed. Read the code on GitHub.

Questions

Claude Code video questions.

Can Claude Code edit videos?

Yes. Claude Code runs ffmpeg to cut and Whisper to write down the words. It cannot watch a video, so it reads the transcript and looks at still frames to check its work. It works best on talking-head videos, where the words carry the edit.

What does it cost to edit videos with Claude Code?

ffmpeg and Whisper are free and run on your computer. Claude Code needs a paid Claude plan or API credits. Takes, the Mac app that sets this up for you, is free and uses your Claude Pro or Max plan.

Is there a Claude Code skill for video editing?

Yes. Several free skills on GitHub make a rough cut with ffmpeg and Whisper. Takes ships its own, takes-video-edit, with tested ffmpeg commands and a rule to check still frames. It also adds the takes MCP server, so any Claude Code session can find your takes.

Can Claude edit videos in Premiere Pro, DaVinci Resolve, Final Cut or CapCut?

Not by itself. Claude Code edits the video files, not the editor. To work inside Premiere Pro or DaVinci Resolve, you need a plugin or MCP server for that editor. Takes makes a normal MP4, so you can open it in any editor for the last touches.

Can I edit YouTube videos with Claude Code?

Yes. One take can give a wide video for YouTube and a 9:16 cut for Shorts. In Takes, Claude also writes the YouTube title and description.

Will I hit the usage limit on the Claude Pro plan?

Cutting and transcribing run on your computer, so they do not use your plan. Claude reads text and a few still frames. Many rounds of notes in one day can reach the Pro limit. Max gives more room.

Does my video get uploaded?

No. The video stays on your computer, and ffmpeg and Whisper run there. Claude sees the transcript and the still frames it checks.

Can Claude Code remove ums and filler words?

Yes. Whisper hides ums by default. Give it a prompt full of fillers (for example "Umm, uh, like, hmm") and they show up in the transcript, so Claude Code can cut them.

Can Claude Code write the social posts for my video?

Yes. It reads the transcript of the final cut and writes a post for each platform. In Takes you see each post the way LinkedIn, X, YouTube or TikTok will show it.

Does this work on Windows?

The by-hand way works anywhere Claude Code, ffmpeg and Whisper run, Windows too. Takes is a Mac app (Apple silicon, macOS 15 or later).

Can it add motion graphics?

Yes, with extra tools such as Remotion or HyperFrames. That needs more setup than this guide covers.

More about Takes

One app, from script to post.

Copied. Paste it in Terminal.