Skip to content

“Claude cuts my TikTok”: How this creator is scaling video with AI | Brooke Lacey

How I AI

36m
Transcript

Original podcast

Where to listen

Summary

Written by a model from the transcript; not yet reviewed.

This episode explores how creator Brooke Lacy uses Claude code and local computer tools to automate short form video editing and scale her content production. The guest explains how she avoids tedious manual trimming and timeline editing by having Claude interact directly with raw video files, local transcription data, and facial tracking scripts to produce perfectly timed TikTok videos complete with custom captions and dynamic cropping. Throughout the conversation, the host and guest discuss the technical workflow of pairing downloaded video corpora with TikTok comment scraping to generate new content ideas, write scripts, and capture a personal cadence without relying on traditional editors or heavy cloud uploads.

  • Store your TikTok video corpus locally in Google Drive so AI tools can reference your past content and style. 20:31
  • Scrape comment threads from popular posts to gather audience feedback and inspire new video script concepts. 20:47
  • Use existing local utilities like FFmpeg, Whisper, and Python running through a terminal interface to process video edits. 9:26
  • Maintain status and operating system markdown files in your sessions to give your AI tools persistent global memory and instructions. 34:01

Chapters

  1. 0:00
    Intro and AI Editing Demo

    The host introduces the episode and previews a live demonstration of Claude-powered video editing.

  2. 1:16
    Meet Brooke Lacy and Her TikTok Empire

    Brooke Lacy explains her background, follower count, and how she uses Claude code to edit her videos.

  3. 7:31
    Claude Code Workflow Overview

    Brooke walks through the step‑by‑step process of using Claude code to cut, caption, and format a raw video.

  4. 13:17
    Building a Text‑Based Edit File

    She explains how the edit is represented as a plain‑text file that lists cuts, sizes, and labels.

  5. 19:06
    Leveraging TikTok Corpus for Content Ideation

    Brooke describes how she stores her TikTok videos in Google Drive and uses comments to generate new scripts.

  6. 22:35
    Training Claude on Style and Cadence

    She shares how Claude learns her facial expressions, humor, and storytelling style from past videos.

  7. 26:43
    Scaling Production and Live Streaming

    Brooke discusses her posting cadence, plans for live streams, and experimenting with TikTok ads.

  8. 28:21
    Lightning Round Q&A

    The host asks quick questions about age, experience, and prompting Claude when it misbehaves.

  9. 34:57
    Wrap‑Up and Contact Info

    Brooke shares where to find her and thanks listeners for joining the episode.

Highlights

Quotes

  • “No timeline, no project file, no editor.”
    Unnamed speaker · 0:00
  • “Claude descended upon our videos and cut them.”
    Unnamed speaker · 8:44
  • “The finished 15 second vertical ad is playing on the right.”
    Unnamed speaker · 15:11
  • “I love being of this generation that is, I appreciate what technology does.”
    Unnamed speaker · 31:33
  • Firecrawl 1:47–2:30
  • Oros 15:33–15:58

About this episode

Brooke Lacey has been making videos since before Facebook had video, and she built a TikTok audience of more than 290,000 by learning to cut short-form videos herself. With over 25 years in tech, she now builds her own apps, including Zosha, a free mobile app for learning AI. In this episode, Brooke walks me through the Claude Code, FFmpeg, and Whisper workflow that edits her TikToks in about 15 seconds, how she mines her comments for new scripts, and how she runs a weekly short-form operation with no editor. What you’ll learn: How Claude Code edits a raw phone video on her computer in about 15 secondsHow she taught Claude her jump-cut cadenceWhy her TikTok comments became her content briefHow she keeps growing her audience while posting just once a week—and what’s nextWhat over 25 years in tech taught her about this AI moment— Brought to you by: Firecrawl https://firecrawl.dev/howiai—Give your AI agents web data and beyond Auros https://aurosglobal.com/howiai—The human network behind AI — In this episode, we cover: (00:00) Intro and guest welcome (02:30) Brooke’s background in video (06:56) Her first session cutting videos with Claude Code (08:51) Live demo: Claude edits a video in real time (11:05) Walking through the edit chain (15:58) How she taught Claude her cadence, her hooks, and what funny sounds like (25:36) Quick recap (26:20) Posting frequency, live streaming plans, and TikTok ads (28:00) Lightning round: Gen X, wisened experience, and YOLO energy (32:43) When Claude disappoints: the lane OS, status files, and how she prompts it back (34:50) Where to find Brooke and the Zosha app — Tools referenced: • Claude Code: https://claude.ai/code • FFmpeg: https://ffmpeg.org https://ffmpeg.org/ • Whisper (OpenAI): https://openai.com/research/whisper — Other reference: • How I AI episode with John Blackman (91-year-old vibe coder): https://www.lennysnewsletter.com/p/how-a-91-year-old-vibe-coded-a-complex?utm_source=publication-search — Where to find Brooke: TikTok: https://www.tiktok.com/@brookejlacey X: https://x.com/brookejlacey Zosha app: http://zosha.app/ — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Transcript

0:00
36:33

6,136 words · 2 speakers

Topics

  • Claude
  • TikTok
  • Claude code
  • Google Drive
  • Jayla
  • Whisper
  • Zosha
  • Python
  • FFmpeg

Page updated · transcript and summary are machine-generated