skills.rest
kienhaminh
kienhaminhCOMMUNITY
Explore all skills by this author →
GitHub

gemini-video-understanding

Analyze local and YouTube videos with Google's Gemini API for summaries and transcripts.

Updated Sep 16, 2025
Search Tags:#summarization#video#youtube#transcription#gemini#clipping
One-click install
npx skills add https://github.com/kienhaminh/speed-reader --skill gemini-video-understanding-kienhaminh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-video-understanding
Source: https://github.com/kienhaminh/speed-reader/tree/main/.claude/skills/gemini-video-understanding
Command: npx skills add https://github.com/kienhaminh/speed-reader --skill gemini-video-understanding-kienhaminh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates video analysis including summarization, transcription with timestamps and visual context, question answering, and YouTube-enabled processing.

Core Features & Use Cases

  • Video Summarization: Short, structured summaries.
  • Transcription with Timestamps & Visuals: Detailed transcripts with MM:SS marks.
  • Question Answering: Answer queries about video content.
  • YouTube Support: Analyze YouTube videos directly (preview).
  • Video Clipping: Process specific start/end segments.
  • Multi-Video Analysis: Compare up to 10 videos.

Quick Start

Install Gemini and run the analyze_video.py script with a local video.

Frequently Asked Questions about gemini-video-understanding

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

FAQPage Schema
How do I analyze and summarize videos using the Gemini API?▼

Analyze videos with Gemini API by running the analyze_video.py script with a local video file or YouTube URL. The Skill extracts summaries, transcriptions with timestamps, and visual descriptions automatically using Gemini 2.5 or 2.0 models, requiring only a GEMINI_API_KEY for authentication.

Can I extract transcriptions with timestamps from videos?▼

Yes, transcription with timestamps extracts detailed transcripts marked with MM:SS timestamps and visual context descriptions. The Skill processes local files and YouTube videos, handling start_offset and end_offset parameters for segment-specific analysis.

Does this support YouTube video analysis directly?▼

YouTube support enables direct analysis of YouTube videos without downloading. Provide a YouTube URL to the analyze_video.py script, and Gemini processes the video content for summarization, transcription, and question answering.

What are the limitations when uploading videos to the Gemini API?▼

The Gemini Files API enforces a 20 MB upload threshold per file. For larger videos, use video clipping with start_offset and end_offset parameters to process specific segments within the size limit.

Can I compare or analyze multiple videos at once?▼

Multi-video analysis supports processing up to 10 videos simultaneously, enabling cross-video comparison, aggregated insights, and batch question answering through a single Skill workflow.

What models does this Skill support?▼

The Skill supports Gemini 2.5 and 2.0 model variants, including gemini-2.5-pro and gemini-2.0-flash. Select your preferred model when initializing the analyze_video.py script with GEMINI_API_KEY authentication.

Related Skills

Explore More Data & Analytics Skills→
danielctcdanielctc

ai-multimodal

Process audio, images, video, and documents with Google Gemini APIs.

Community
Advanced
zangjeicyzangjeicy

youtube-content

Extract YouTube video transcripts and convert them into summaries, chapters, and blog posts.

Community
Intermediate
locdinh209locdinh209

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced
levanminhduclevanminhduc

gemini-video-understanding

Analyze local and YouTube videos with the Gemini API for summarization and Q&A.

Community
Advanced