Design & media

Media Inspector

Try it

本地音视频文件分析工具。支持扫描媒体文件、提取元数据、语音转文字(Whisper)、生成摘要和关键片段。支持 MP4/MOV/MKV/MP3/WAV/M4A/FLAC 等格式。

What it does

本地音视频文件分析工具。支持扫描媒体文件、提取元数据、语音转文字(Whisper)、生成摘要和关键片段。支持 MP4/MOV/MKV/MP3/WAV/M4A/FLAC 等格式。

The skill document

Media Inspector 📺 🎵

本地音视频文件分析工具,可扫描、提取元数据、转录、摘要和导出报告。

支持格式

视频: mp4, mov, mkv, avi, webm, m4v, ts, mpg, mpeg
音频: mp3, wav, m4a, aac, flac, ogg, opus, aiff, wma

快速开始

1. 扫描媒体文件

python scripts/scan_media.py /path/to/media --out-dir ./media_scan

输出文件:

  • scan_results.json - JSON格式
  • scan_results.csv - CSV格式
  • scan_results.md - Markdown格式

2. 深度分析

python scripts/analyze_media.py /path/to/file.mp4 --out-dir ./media_analysis

分析内容:

  1. 元数据提取(ffprobe)
  2. 语音转文字(Whisper,可选)
  3. 内容摘要
  4. 关键片段提取(带时间戳)
  5. 报告导出(JSON/CSV/Markdown)

依赖安装

# 必需:ffmpeg (包含 ffprobe)
brew install ffmpeg

# 可选:Whisper 语音转文字
pip install whisper
# 或
brew install whisper

使用规则

  • ✅ 优先使用转录文本进行分析,不要仅凭文件名猜测
  • ⚠️ Whisper 不可用时,明确告知用户并仅返回元数据
  • ❌ 不要虚构内容摘要
  • 📝 关键片段必须包含时间戳
  • 📊 批量分析时,每个文件单独报告

输出示例

扫描报告

# Media Scan Report

## Summary
- scanned path: /path/to/media
- files found: 10
- audio files: 3
- video files: 7

## Candidates
| filename | duration | type | file size |
|---|---|---|---|
| video.mp4 | 01:30:00 | video | 500.2 MB |
| audio.mp3 | 00:05:30 | audio | 5.2 MB |

分析报告

# Media Analysis Report

## File
- path: /path/to/video.mp4
- type: video
- duration: 01:30:00

## Transcript
- available: yes
- whisper used: yes

## Summary
[基于转录文本的摘要内容]

## Key excerpts
1. [00:01:30 - 00:02:15] 关键片段内容...
2. [00:15:00 - 00:16:30] 另一个关键片段...

Related skills

从本地视频文件中提取语音文案/字幕。当用户提供视频文件路径(MP4等)要求提取文案、字幕、语音转文字时触发。跨平台支持(macOS/Windows/Linux),完全离线运行。

Diagnose playback and streaming problems in user-provided media files and URLs (m3u8 / HTTP / RTMP / RTSP / SRT): moov atom position, codec compatibility (H.265/HEVC, AAC-HE, 10-bit), container issues, HLS playlist and TS segment integrity, bitrate/frame-rate anomalies, audio-video sync, and live latency factors such as B-frames and GOP size. Use when the user reports a video that will not play, shows a black or green screen, stutters or buffers, or asks for an HLS playlist, TS segment, or live stream latency check. Read-only. No credentials and no cloud API calls. Triggers: "video file won't play", "video black screen or green screen", "moov atom position issue", "HLS m3u8 playlist check", "HLS segment corrupted", "live stream latency or stutter", "TS segment analysis", "video codec compatibility", "media file format diagnosis", "B-frame or GOP structure analysis".

Offline-first workflow for turning Chinese web page video or audio into text and Word deliverables. Use when Codex needs to (1) extract playable media stream...

14 installs

视频分析处理 — 本地视频反编译分析工具。将视频拆解为时间轴剧本、语音转文字、场景分析、跨模态关联和精华摘要,支持多ASR引擎切换(Whisper/Paraformer/SenseVoice)、中文NLP增强、PaddleOCR中文识别。v4.0 新增短视频平台适配(抖音/快手/B站/视频号)和自动剪辑建议(高光检测/冗余标记/EDL导出/字幕样式)。v4.1 新增tiny模型优先体验(75MB低门槛)、说话人分离质量评分、剪映draft.json导出。v4.2 新增场景管理(detect→slice一条链)、短视频爆款预测、实时直播分析(流式ASR+敏感词检测)。v4.3 新增纯音频输入(mp3/m4a/wav播客与录音)、批量队列(SQLite+硬件档位并发)、GPU自动加速(CT2 int8量化)、ASR配置统一(--asr-engine单参数)。

Transcribe audio and video with the transcribe.so CLI. Turns YouTube videos, podcasts (Apple Podcasts, Spotify, SoundCloud, Vimeo, Twitch, Loom), direct media URLs, and local audio or video files into speaker-labelled transcripts with timestamped segments, chapters, sections, cited Q&A, and subtitle files (SRT, VTT, karaoke VTT). Use when the user wants a transcript, show notes, chapters, subtitles, quotes, or answers grounded in a recording. 52 languages and dialects.