skills.rest
hanzoai
hanzoaiOFFICIAL
Explore all skills by this author →
Website𝕏@hanzoaiGitHub

video-understand

Extract frames and transcribe audio from local videos into structured JSON.

Updated Aug 27, 2026
Search Tags:#analysis#offline#transcription#whisper#ffmpeg#video-understanding#frame-extraction
One-click install
npx skills add https://github.com/hanzoai/video --skill video-understand-hanzoai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video-understand
Source: https://github.com/hanzoai/video/tree/main/.agents/skills/video-understand
Command: npx skills add https://github.com/hanzoai/video --skill video-understand-hanzoai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Understand video content locally by extracting frames with ffmpeg and transcribing audio with Whisper, all without cloud keys or API access needed.

Core Features & Use Cases

  • Offline video understanding: extract frames for visual analysis and transcribe speech without internet.
  • Flexible extraction modes: scene-based, keyframe, or interval frame sampling.
  • Output: structured JSON with video metadata, frames, and transcript.

Quick Start

Run understand_video on a local video file to produce a frames-and-transcript JSON.

Frequently Asked Questions about video-understand

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract frames and transcribe audio from a video offline?▼

To extract frames and transcribe audio offline, use ffmpeg for visual frame extraction and Whisper for speech-to-text transcription, outputting structured JSON containing video metadata, frames, and transcript.

What is the best way to do offline video understanding without cloud API keys?▼

Offline video understanding without cloud API keys is achieved by running local Python scripts that orchestrate ffmpeg and optional Whisper to analyze local video files and output structured JSON.

Does offline video transcription with Whisper require an internet connection?▼

Offline video transcription with Whisper does not require an internet connection. It operates locally on your machine to transcribe speech from video files without needing cloud API access.

Can I extract keyframes from a local video file using ffmpeg for analysis?▼

Yes, you can extract keyframes from a local video file using ffmpeg. The tool supports flexible extraction modes including scene-based, keyframe, or interval frame sampling for visual analysis.

Do I need ffprobe installed to extract scene-based frames from local videos?▼

Yes, you need ffprobe installed along with ffmpeg to extract scene-based frames. These offline tools are required by the Python scripts to orchestrate frame extraction and video metadata analysis.

What format does offline video frame extraction output for downstream analysis?▼

Offline video frame extraction outputs structured JSON. This format combines extracted video metadata, sampled frames, and the audio transcript into a single structured file for downstream analysis.

Related Skills

Explore More Data & Analytics Skills→
viticciviticci
234

frames-cli

Apply Apple device bezels to screenshots and videos via command line.

Community
Advanced
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
gyalamanch001agyalamanch001a

video-understand

Extract frames and transcribe speech from video files into structured JSON.

Community
Advanced
xingBaGanxingBaGan

video-understand

Analyze video content and transcribe audio locally with ffmpeg and Whisper.

Community
Intermediate