Claude Code edited my TikTok
A creator describes using Claude Code to automatically edit their TikTok videos by analyzing raw footage and verbal instructions. The AI tool uses existing computer tools like FFmpeg, Whisper, and Python to process local files, intelligently cutting segments based on spoken cues and selecting the best takes.
Summary
The speaker describes their experience having Claude Code edit a TikTok video from raw, uncut footage. They initially recorded 25-30 minutes of continuous video without any editing or stopping. Rather than manually editing, they used Claude Code by AirDropping the file to their computer and asking it to edit the video. The key innovation is that Claude Code doesn't require uploading files anywhere—it simply runs locally on the computer using existing tools already installed (FFmpeg, Whisper, and Python). The speaker was impressed by Claude's ability to listen to their verbal instructions ("cut that out") and understand what they meant. Beyond basic cutting, Claude demonstrated advanced editing judgment by identifying repeated sections in the video and automatically selecting the take with the best cadence, showing it could make creative editing decisions beyond simple command execution.
Key Insights
- Claude Code processes video files entirely locally using existing computer tools (FFmpeg, Whisper, Python) without uploading files anywhere, keeping all processing on the user's machine
- Claude Code can understand verbal instructions from the speaker (like 'cut that out') and execute them on the video file automatically
- Claude Code demonstrated the ability to identify repeated segments across a video and intelligently select the version with the best cadence without being explicitly instructed to do so
- The speaker initially recorded 25-30 minutes of unedited footage as a single continuous take, expecting to edit it manually before using Claude Code
- Claude Code can open and display the finished edited video directly to the user after completing the editing task
Topics
Transcript
[0:00] What just happened is Claude descended upon our videos and cut them. >> I probably did 25 to 30 minutes of just the whole thing. Didn't cut it up. Didn't stop the video. It was just all of it. And then I'd be like, "Ah, no. Cut that out." Meaning I was saying it to me and then I air dropped to the computer and I go on to cloud code and was like, "Let's see what you got, my dude." And it just used the boring tools that are already on our computers. FFmpeg, Whisper, Python. It didn't upload the video anywhere. The files are [0:30] in the computer. The only thing that's happening is the instructions are…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
I Turned a $50 Photo Frame Into an AI Family Dashboard
A creator transformed a $50 Amazon photo frame running Android into a customized AI-powered family dashboard using OpenAI's Codeex and web technologies. The dashboard displays family schedules, photos, NASA images, news, and individual checklists for each family member, with updates automatically posted via an API connected to a grabbot that monitors calendars and emails.
Claude Code for creators: AI editing is here
Brooke Lacey, a 200K+ TikTok creator, demonstrates how she uses Claude Code to automate short-form video editing by leveraging existing computer tools like FFmpeg, Whisper, and Python without uploading files to the cloud. She trains Claude on her TikTok corpus to understand her editing style, facial expressions, and comedic timing, then uses it to generate jump cuts, captions, scripts, and mine comments for new content ideas.
Muse dodged every trap in this billing ticket
A billing ticket resolution task was used to benchmark agentic AI performance, and Muse excelled by successfully navigating multiple challenges including account linking errors, duplicate refund issues, and prompt injection attempts. The agent demonstrated superior performance by investigating thoroughly, fixing the account link, issuing the correct refund, updating the plan, and marking the ticket as resolved.
Meta's Muse is the best AI agent I've tested
The speaker provides their initial impressions of Meta's Muse AI agent, declaring it the best agentic AI they've tested. Muse excelled across four different knowledge work tasks including billing management, customer responses, inbox triage, and research, outperforming alternatives.
Meta's Muse: best AI agent, worst designer
The speaker tests Meta's AI model on video editing and finds it excels at technical tasks like cutting and timing but significantly underperforms on creative work like design and overlays. They conclude that while the model is strong for coding and agent tasks, it falls short compared to Claude Opus 3.5 for creative applications.