视频摘要生成器 - 一键下载1800+平台视频并生成字幕、转录稿和摘要

video-summarizer by liang121/video-summarizer

231 周安装量

15 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/liang121/video-summarizer --skill video-summarizer

内容创作自动化自然语言处理

🇨🇳中文介绍

视频摘要生成器

概述

从任意平台下载视频并生成完整的资源包，包括：

原始视频文件 (mp4)
音频文件 (mp3)
字幕文件 (带时间戳，vtt/srt 格式)
摘要文件 (summary.md)

支持 yt-dlp 支持的所有 1800+ 个网站。

触发条件

当用户：

提供视频链接并要求摘要
说“总结这个视频”、“这个视频讲了什么”
要求“提取视频内容”、“转录视频”
说“下载这个视频”
提供来自 YouTube/Bilibili/Twitter/Vimeo/TikTok 等的链接

支持平台

YouTube (youtube.com, youtu.be)
Bilibili (bilibili.com, b23.tv)
Twitter/X (x.com, twitter.com)
Vimeo (vimeo.com)
TikTok (tiktok.com)
Instagram (instagram.com)
Twitch (twitch.tv)
以及 1800+ 其他平台 (yt-dlp 支持的所有站点)

输出结构

所有文件都保存在当前工作目录下的 downloads/<视频标题>/ 中：

./downloads/
└── <video-title>/
    ├── video.mp4          # 原始视频
    ├── audio.mp3          # 提取的音频
    ├── subtitle.vtt       # 带时间戳的字幕
    ├── transcript.txt     # 纯文本转录稿 (无时间戳)
    └── summary.md         # 结构化摘要

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

步骤 1：安装依赖项

运行安装脚本以检查和安装所有依赖项：

bash "$SKILL_DIR/scripts/install_deps.sh"

这将安装：uv (Python 包管理器)、ffmpeg、yt-dlp，并检查 Python 版本。faster-whisper 将由 uv 自动管理。

步骤 2：获取视频信息并创建输出目录

# 获取视频标题 (为文件夹名称清理特殊字符)
TITLE=$(yt-dlp --print "%(title)s" "VIDEO_URL" | sed 's/[/:*?"<>|]/_/g' | cut -c1-80)
DURATION=$(yt-dlp --print "%(duration)s" "VIDEO_URL")

# 创建输出目录
OUTPUT_DIR=./downloads/"$TITLE"
mkdir -p "$OUTPUT_DIR"

步骤 3：下载视频和音频

# 下载视频 (mp4 格式，最高 1080p 的最佳质量)
yt-dlp -f "bestvideo[height<=1080][ext=mp4]+bestaudio[ext=m4a]/best[height<=1080][ext=mp4]/best" \
  --merge-output-format mp4 \
  -o "$OUTPUT_DIR/video.%(ext)s" "VIDEO_URL"

# 提取音频 (mp3 格式)
yt-dlp -x --audio-format mp3 -o "$OUTPUT_DIR/audio.%(ext)s" "VIDEO_URL"

步骤 4：获取字幕

优先级顺序：

尝试下载手动字幕 (最佳质量)

yt-dlp --write-subs --sub-lang zh,en,zh-Hans,zh-Hant --skip-download \

  -o "$OUTPUT_DIR/subtitle" "VIDEO_URL"

2. 尝试下载自动生成的字幕

yt-dlp --write-auto-subs --sub-lang zh,en --skip-download \
  -o "$OUTPUT_DIR/subtitle" "VIDEO_URL"

3. 当无字幕可用时，使用 faster-whisper 进行转录

uv run "$SKILL_DIR/scripts/parallel_transcribe.py" \
  --input "$OUTPUT_DIR/audio.mp3" \
  --output-dir "$OUTPUT_DIR" \
  --model small \
  --language auto

脚本自动执行：

在静音点处分割长音频文件
使用多个 CPU 核心进行并行转录
输出 subtitle.vtt 和 transcript.txt

选项	默认值	描述
`--model`	small	tiny/base/small/medium/large-v3
`--language`	auto	语言代码或 'auto'
`--workers`	CPU/2	并行工作线程数
`--min-segment`	60	启用分割的最小时长 (秒)

步骤 5：生成纯文本转录稿

如果下载了字幕 (非转录)，则转换为纯文本：

if [[ ! -f "$OUTPUT_DIR/transcript.txt" ]]; then
  SUBTITLE_FILE=$(ls "$OUTPUT_DIR"/*.vtt "$OUTPUT_DIR"/*.srt 2>/dev/null | head -1)
  if [[ "$SUBTITLE_FILE" == *.vtt ]]; then
    sed '/^[0-9]/d; /^$/d; /-->/d; /^WEBVTT/d; /^Kind:/d; /^Language:/d; /^NOTE/d' \
      "$SUBTITLE_FILE" > "$OUTPUT_DIR/transcript.txt"
  elif [[ "$SUBTITLE_FILE" == *.srt ]]; then
    sed '/^[0-9]/d; /^$/d; /-->/d' "$SUBTITLE_FILE" > "$OUTPUT_DIR/transcript.txt"
  fi
fi

步骤 6：生成摘要文件

从 $SKILL_DIR/reference/summary-prompt.md 读取提示模板
替换占位符：{{TITLE}}、{{PLATFORM}}、{{URL}}、{{DURATION}}、{{LANGUAGE}}、{{DOWNLOAD_TIME}}、{{TRANSCRIPT}}
生成摘要并保存到 $OUTPUT_DIR/summary.md

# 优先中文字幕
yt-dlp --sub-lang zh-Hans,zh-Hant,zh ...
# 如果需要登录
yt-dlp --cookies-from-browser chrome "VIDEO_URL"

需要登录的平台

yt-dlp --cookies-from-browser chrome "VIDEO_URL"
# 或 firefox
yt-dlp --cookies-from-browser firefox "VIDEO_URL"

使用并行转录脚本 (步骤 4，选项 3)。

视频过长 (>1 小时)

询问用户是否只需要部分内容
并行脚本会自动处理长文件

yt-dlp --list-extractors | grep -i "platform-name"

存储：文件保存在当前工作目录下的 ./downloads/
版权：仅限个人学习使用
网络：某些平台可能需要代理
首次运行：需要下载 Whisper 模型 (small 约 244MB)
并行处理：长音频 (>60秒) 会在静音点自动分割

🇺🇸English

Video Summarizer

Overview

Download videos from any platform and generate a complete resource package including:

Original video file (mp4)
Audio file (mp3)
Subtitle file (with timestamps, vtt/srt format)
Summary file (summary.md)

Supports all 1800+ websites supported by yt-dlp.

Trigger Conditions

When the user:

Provides a video link and asks for a summary
Says "summarize this video", "what's in this video"
Asks to "extract video content", "transcribe video"
Says "download this video"
Provides a link from YouTube/Bilibili/Twitter/Vimeo/TikTok etc.

Supported Platforms

YouTube (youtube.com, youtu.be)
Bilibili (bilibili.com, b23.tv)
Twitter/X (x.com, twitter.com)
Vimeo (vimeo.com)
TikTok (tiktok.com)
Instagram (instagram.com)
Twitch (twitch.tv)
And 1800+ other platforms (all sites supported by yt-dlp)

Output Structure

All files are saved to downloads/<video-title>/ in the current working directory :

./downloads/
└── <video-title>/
    ├── video.mp4          # Original video
    ├── audio.mp3          # Extracted audio
    ├── subtitle.vtt       # Subtitles with timestamps
    ├── transcript.txt     # Plain text transcript (no timestamps)
    └── summary.md         # Structured summary

Workflow

Step 1: Install Dependencies

Run the install script to check and install all dependencies:

bash "$SKILL_DIR/scripts/install_deps.sh"

This installs: uv (Python package manager), ffmpeg, yt-dlp, and checks Python version. faster-whisper will be automatically managed by uv.

Step 2: Get Video Info and Create Output Directory

# Get video title (sanitize special characters for folder name)
TITLE=$(yt-dlp --print "%(title)s" "VIDEO_URL" | sed 's/[/:*?"<>|]/_/g' | cut -c1-80)
DURATION=$(yt-dlp --print "%(duration)s" "VIDEO_URL")

# Create output directory
OUTPUT_DIR=./downloads/"$TITLE"
mkdir -p "$OUTPUT_DIR"

Step 3: Download Video and Audio

# Download video (mp4 format, best quality up to 1080p)
yt-dlp -f "bestvideo[height<=1080][ext=mp4]+bestaudio[ext=m4a]/best[height<=1080][ext=mp4]/best" \
  --merge-output-format mp4 \
  -o "$OUTPUT_DIR/video.%(ext)s" "VIDEO_URL"

# Extract audio (mp3 format)
yt-dlp -x --audio-format mp3 -o "$OUTPUT_DIR/audio.%(ext)s" "VIDEO_URL"

Step 4: Get Subtitles

Priority order:

Try downloading manual subtitles (best quality)

yt-dlp --write-subs --sub-lang zh,en,zh-Hans,zh-Hant --skip-download \

  -o "$OUTPUT_DIR/subtitle" "VIDEO_URL"

2. Try downloading auto-generated subtitles

yt-dlp --write-auto-subs --sub-lang zh,en --skip-download \
  -o "$OUTPUT_DIR/subtitle" "VIDEO_URL"

3. Use faster-whisper transcription when no subtitles available

uv run "$SKILL_DIR/scripts/parallel_transcribe.py" \
  --input "$OUTPUT_DIR/audio.mp3" \
  --output-dir "$OUTPUT_DIR" \
  --model small \
  --language auto

The script automatically:

Splits long audio files at silence points
Uses multiple CPU cores for parallel transcription
Outputs both subtitle.vtt and transcript.txt

Transcription Options :

Option	Default	Description
`--model`	small	tiny/base/small/medium/large-v3
`--language`	auto	Language code or 'auto'
`--workers`	CPU/2	Number of parallel workers
`--min-segment`	60	Min duration (sec) to enable splitting

Step 5: Generate Plain Text Transcript

If subtitles were downloaded (not transcribed), convert to plain text:

if [[ ! -f "$OUTPUT_DIR/transcript.txt" ]]; then
  SUBTITLE_FILE=$(ls "$OUTPUT_DIR"/*.vtt "$OUTPUT_DIR"/*.srt 2>/dev/null | head -1)
  if [[ "$SUBTITLE_FILE" == *.vtt ]]; then
    sed '/^[0-9]/d; /^$/d; /-->/d; /^WEBVTT/d; /^Kind:/d; /^Language:/d; /^NOTE/d' \
      "$SUBTITLE_FILE" > "$OUTPUT_DIR/transcript.txt"
  elif [[ "$SUBTITLE_FILE" == *.srt ]]; then
    sed '/^[0-9]/d; /^$/d; /-->/d' "$SUBTITLE_FILE" > "$OUTPUT_DIR/transcript.txt"
  fi
fi

Step 6: Generate Summary File

Read prompt template from $SKILL_DIR/reference/summary-prompt.md
Replace placeholders: {{TITLE}}, {{PLATFORM}}, {{URL}}, {{DURATION}}, {{LANGUAGE}}, {{DOWNLOAD_TIME}}, {{TRANSCRIPT}}
Generate summary and save to $OUTPUT_DIR/summary.md

Platform-Specific Handling

Bilibili

# Prioritize Chinese subtitles
yt-dlp --sub-lang zh-Hans,zh-Hant,zh ...
# If login required
yt-dlp --cookies-from-browser chrome "VIDEO_URL"

Platforms Requiring Login

yt-dlp --cookies-from-browser chrome "VIDEO_URL"
# or firefox
yt-dlp --cookies-from-browser firefox "VIDEO_URL"

Error Handling

Cannot Get Subtitles

Use the parallel transcription script (Step 4, option 3).

Video Too Long (>1 hour)

Ask user if they only need partial content
The parallel script handles long files automatically

Unsupported Platform

yt-dlp --list-extractors | grep -i "platform-name"

Notes

Storage : Files saved to ./downloads/ in current working directory
Copyright : For personal learning use only
Network : Some platforms may require proxy
First Run : Whisper model download required (~244MB for small)
Parallel Processing : Long audio (>60s) auto-splits at silence points

Weekly Installs

231

Repository

liang121/video-…mmarizer

GitHub Stars

First Seen

Feb 4, 2026

Security Audits

Gen Agent Trust HubFail SocketWarn SnykWarn

Installed on

opencode230

gemini-cli229

codex228

cursor228

kimi-cli227

amp227

Skills CLI 使用指南：AI Agent 技能包管理器安装与管理教程

27,400 周安装

视频摘要生成器 - 一键下载1800+平台视频并生成字幕、转录稿和摘要

🇨🇳中文介绍

视频摘要生成器

概述

触发条件

支持平台

输出结构

相关 Skills

工作流程

步骤 1：安装依赖项

步骤 2：获取视频信息并创建输出目录

步骤 3：下载视频和音频

步骤 4：获取字幕

步骤 5：生成纯文本转录稿

步骤 6：生成摘要文件

平台特定处理

Bilibili

需要登录的平台

错误处理

无法获取字幕

视频过长 (>1 小时)

不支持的平台

注意事项

🇺🇸English

Video Summarizer

Overview

Trigger Conditions

Supported Platforms

Output Structure

Workflow

Step 1: Install Dependencies

Step 2: Get Video Info and Create Output Directory

Step 3: Download Video and Audio

Step 4: Get Subtitles

Step 5: Generate Plain Text Transcript

Step 6: Generate Summary File

Platform-Specific Handling

Bilibili

Platforms Requiring Login

Error Handling

Cannot Get Subtitles

Video Too Long (>1 hour)

Unsupported Platform

Notes

最新 Skills