Skill: Raw Video Processing

Prerequisite: FFmpeg and Python 3 must be installed.

When to Use

• Long pauses / dead air while thinking or waiting for loading
• Overall pacing feels slow and could benefit from a slight speed boost

Default Workflow

Step 1: Remove Silent Segments

python /path/to/skills/raw-video-processing/scripts/remove_silence.py <input.mp4>

<input>_nosilence.mp4

• --threshold -30dB

  — silence detection sensitivity

• --duration 0.8

  — minimum silence length (seconds) to remove

• --padding 0.2

  — seconds of breathing room kept around speech boundaries

Step 2: Speed Up the Video

python /path/to/skills/raw-video-processing/scripts/speed_video.py <input>_nosilence.mp4

<input>_nosilence_1.2x.mp4

• --speed 1.2

  — 1.2x playback speed (a subtle boost that doesn't feel rushed)

Script Options

remove_silence.py

-o

--output

<input>_nosilence.mp4

-t

--threshold

-30dB

-d

--duration

0.8

-p

--padding

0.2

--dry-run

speed_video.py

-o

--output

<input>_<speed>x.mp4

-s

--speed

1.2

Custom Scenarios

• Only remove silence — run just Step 1.
• Only speed up — run just Step 2 directly on the input file.
• Aggressive cleanup — use

  --threshold -25dB --duration 0.5

  for stricter silence removal, and

  --speed 1.5

  for faster playback.
• Preview before committing — use

  --dry-run

  on remove_silence.py to see what would be cut without creating a file.
• Custom output name — use

  -o

  on either script to control the output path.

Important Notes

• Always run remove_silence before speed_video. Silence detection works on the original audio; speeding up first would alter the audio characteristics and make silence detection less accurate.
• For long videos (>30 min), the silence removal step may take a few minutes as it processes each segment individually.
• Both scripts preserve video quality — remove_silence uses stream copy (no re-encoding), while speed_video re-encodes with FFmpeg defaults.