AragornZJF/video-clip-assistant

Video Clip Assistant

Automated video clipping assistant. Based on FFmpeg, it provides video trimming, subtitle generation, short video export, and more.

Core Capabilities

1. Timeline Trimming — Extract clips by timestamp
2. Keyword Slicing — Find segments matching keywords via ASR subtitles
3. Subtitle Burning — Burn SRT subtitles into video
4. Short Video Export — Crop to 9:16 / 1:1 / 16:9 multi-ratios
5. Highlight Extraction — Automatically extract highlight segments from long videos

Quick Start

Trim by Time

python3 scripts/cut_video.py --input video.mp4 --start 10 --duration 30 --output clip.mp4

Extract Multiple Segments

python3 scripts/cut_video.py --input video.mp4 --segments "0-30,60-90,120-150" --output ./clips/

Burn Subtitles

python3 scripts/burn_subtitles.py --input video.mp4 --srt subs.srt --output subtitled.mp4

Export Short Video

python3 scripts/export_social.py --input video.mp4 --format vertical --duration 60 --output shorts/

Scripts Overview

scripts/cut_video.py

Trim video by timeline.

python3 scripts/cut_video.py \
  --input <video_file> \
  --start <seconds> \
  --duration <seconds> \
  [--segments "0-30,60-90"] \
  --output <output>

scripts/burn_subtitles.py

Burn SRT subtitles into video.

python3 scripts/burn_subtitles.py \
  --input <video> \
  --srt <subtitle_file> \
  --output <output>

Supports custom subtitle position, font size, and color.

scripts/export_social.py

Export to multi-platform compatible format.

python3 scripts/export_social.py \
  --input <video> \
  --format <vertical|square|horizontal> \
  --duration <seconds> \
  --output <output_directory>

Format	Ratio	Use Case
vertical	9:16	TikTok / Kuaishou / Xiaohongshu
square	1:1	Instagram
horizontal	16:9	YouTube / Bilibili

scripts/extract_highlights.py

Automatically extract highlight segments from a long video.

python3 scripts/extract_highlights.py \
  --input <video> \
  --num-clips <number_of_clips> \
  --min-duration <minimum_seconds> \
  --output <output_directory>

Uses scene detection algorithm to locate interesting transition points.

scripts/generate_subtitles.py

Generate SRT subtitle file (requires ASR service).

python3 scripts/generate_subtitles.py \
  --input <video> \
  --provider <whisper|funclip> \
  --output <subtitles.srt>

Typical Workflows

Workflow 1: Extract 3 highlight clips from a meeting recording

# 1. Cut 3 segments
python3 scripts/cut_video.py \
  --input meeting.mp4 \
  --segments "300-360,720-780,1200-1260" \
  --output ./clips/

# 2. Export each for TikTok format
for f in ./clips/*.mp4; do
  python3 scripts/export_social.py \
    --input "$f" \
    --format vertical \
    --output ./shorts/
done

Workflow 2: Add subtitles to a video

# 1. Generate subtitles
python3 scripts/generate_subtitles.py \
  --input video.mp4 \
  --provider whisper \
  --output video.srt

# 2. Burn subtitles
python3 scripts/burn_subtitles.py \
  --input video.mp4 \
  --srt video.srt \
  --output subtitled.mp4

Workflow 3: One-click generate multiple short videos

python3 scripts/export_social.py \
  --input long_video.mp4 \
  --format vertical \
  --duration 60 \
  --output ./shorts/

Environment Requirements

• Required: FFmpeg (ffmpeg / ffprobe)
• Optional: FunClip (Alibaba open-source ASR video clipping)
• Optional: Whisper (local or API mode)

Installation Reference

# Install FunClip (recommended)
pip install funclip

# Install Whisper
pip install openai-whisper

# FFmpeg (already installed)
which ffmpeg  # should return a path