Screen Studio / raw footage
  → Claude / Codex
  → FFmpeg
  → Remotion
  → ElevenLabs / fal.ai
  → Descript or CapCut

Example prompt:
"Here's the transcript of a 4-hour recording. Identify the 8 strongest segments
for a 24-minute vlog. Give me FFmpeg cut commands for each segment."

ffmpeg -i raw.mp4 -ss 00:12:30 -to 00:15:45 -c copy segment_01.mp4

#!/bin/bash
# cuts.txt: start,end,label
while IFS=, read -r start end label; do
  ffmpeg -i raw.mp4 -ss "$start" -to "$end" -c copy "segments/${label}.mp4"
done < cuts.txt

# Create file list
for f in segments/*.mp4; do echo "file '$f'"; done > concat.txt
ffmpeg -f concat -safe 0 -i concat.txt -c copy assembled.mp4

ffmpeg -i raw.mp4 -vf "scale=960:-2" -c:v libx264 -preset ultrafast -crf 28 proxy.mp4

ffmpeg -i raw.mp4 -vn -acodec pcm_s16le -ar 16000 audio.wav

ffmpeg -i segment.mp4 -af loudnorm=I=-16:TP=-1.5:LRA=11 -c:v copy normalized.mp4

import { AbsoluteFill, Sequence, Video, useCurrentFrame } from "remotion";

export const VlogComposition: React.FC = () => {
  const frame = useCurrentFrame();

  return (
    <AbsoluteFill>
      {/* Main footage */}
      <Sequence from={0} durationInFrames={300}>
        <Video src="/segments/intro.mp4" />
      </Sequence>

      {/* Title overlay */}
      <Sequence from={30} durationInFrames={90}>
        <AbsoluteFill style={{
          justifyContent: "center",
          alignItems: "center",
        }}>
          <h1 style={{
            fontSize: 72,
            color: "white",
            textShadow: "2px 2px 8px rgba(0,0,0,0.8)",
          }}>
            The AI Editing Stack
          </h1>
        </AbsoluteFill>
      </Sequence>

      {/* Next segment */}
      <Sequence from={300} durationInFrames={450}>
        <Video src="/segments/demo.mp4" />
      </Sequence>
    </AbsoluteFill>
  );
};

npx remotion render src/index.ts VlogComposition output.mp4

import os
import requests

resp = requests.post(
    f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}",
    headers={
        "xi-api-key": os.environ["ELEVENLABS_API_KEY"],
        "Content-Type": "application/json"
    },
    json={
        "text": "Your narration text here",
        "model_id": "eleven_turbo_v2_5",
        "voice_settings": {"stability": 0.5, "similarity_boost": 0.75}
    }
)
with open("voiceover.mp3", "wb") as f:
    f.write(resp.content)

generate(app_id: "fal-ai/nano-banana-pro", input_data: {
  "prompt": "professional thumbnail for tech vlog, dark background, code on screen",
  "image_size": "landscape_16_9"
})

voiceover = coll.generate_voice(text="Narration here", voice="alloy")
music = coll.generate_music(prompt="lo-fi background for coding vlog", duration=120)
sfx = coll.generate_sound_effect(prompt="subtle whoosh transition")

# 16:9 to 9:16 (center crop)
ffmpeg -i input.mp4 -vf "crop=ih*9/16:ih,scale=1080:1920" vertical.mp4

# 16:9 to 1:1 (center crop)
ffmpeg -i input.mp4 -vf "crop=ih:ih,scale=1080:1080" square.mp4

from videodb import ReframeMode

# Smart reframe (AI-guided subject tracking)
reframed = video.reframe(start=0, end=60, target="vertical", mode=ReframeMode.smart)

# Detect scene changes (threshold 0.3 = moderate sensitivity)
ffmpeg -i input.mp4 -vf "select='gt(scene,0.3)',showinfo" -vsync vfr -f null - 2>&1 | grep showinfo

# Find silent segments (useful for cutting dead air)
ffmpeg -i input.mp4 -af silencedetect=noise=-30dB:d=2 -f null - 2>&1 | grep silence

"Given this transcript with timestamps and these scene change points,
identify the 5 most engaging 30-second clips for social media."