video-to-subtitle-summary

Converts online or local videos to subtitles and generates AI summaries.

153|14|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/imlewc/video-to-subtitle-summary-skill --skill video-to-subtitle-summary
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-to-subtitle-summary
Source: https://github.com/imlewc/video-to-subtitle-summary-skill/tree/main
Command: npx skills add https://github.com/imlewc/video-to-subtitle-summary-skill --skill video-to-subtitle-summary

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, ffmpeg, yt-dlp, faster-whisper, volcengine, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the process of converting videos into subtitles and generating AI-driven summaries, saving you time and effort.

Core Features & Use Cases

  • Video to Subtitle: Automatically convert video content into subtitle text.
  • AI Summarization: Generate AI-driven summaries of video content.
  • Use Case: Quickly get a summary of a long video, or convert online videos or local files into subtitles for accessibility.

Quick Start

To extract subtitles and summarize a video, use the following command:

/video-to-subtitle-summary https://v.douyin.com/xxxxxx/

Frequently Asked Questions about video-to-subtitle-summary

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

FAQPage Schema
How do I extract subtitles and generate a summary from a YouTube video URL?

To extract subtitles and generate a summary, provide the online video URL to the tool. It fetches the video, transcribes the audio into subtitle text, and uses AI to produce a concise content summary.

Can I use this to transcribe local video and audio files into subtitles?

Yes, you can convert local video and audio files into subtitles. The tool processes local media paths directly, utilizing ASR backends like faster-whisper or Volcengine to transcribe the audio track accurately.

Do I need Python and FFmpeg installed to convert videos to subtitles?

Yes, Python and FFmpeg are required dependencies for this video to subtitle conversion. You also need yt-dlp for fetching online videos and an ASR backend like faster-whisper or Volcengine for speech recognition.

What's the best way to get an AI summary of a long video on Bilibili or Douyin?

To get an AI summary of a long video, input the Douyin or Bilibili URL. The tool downloads the content, transcribes it into text, and automatically generates an AI-driven summary to save you time.

Does faster-whisper work with Volcengine for video subtitle generation?

faster-whisper and Volcengine VC function as alternative ASR backends for video subtitle generation. You can configure either backend to transcribe the audio track into text depending on your environment.

Why does online video subtitle extraction require yt-dlp?

Online video subtitle extraction requires yt-dlp to fetch video content from platforms like YouTube, Douyin, and Xiaohongshu. It downloads the media stream locally so the ASR backend can process the audio for transcription.