Transcribe local videos into timestamped text and extracted keyframes.
npx skills add https://github.com/RonanCodes/llm-wiki --skill ingest-video
Please help me install this Agent Skill. Skill: ingest-video Source: https://github.com/RonanCodes/llm-wiki/tree/main/.claude/skills/ingest-video Command: npx skills add https://github.com/RonanCodes/llm-wiki --skill ingest-video
Local video files such as meetings, presentations, and screen recordings are often locked as opaque media that are hard to search, summarize, or integrate into a knowledge base. This Skill automates transcription, speaker attribution, and screenshot extraction so video content becomes searchable, citable, and summarized inside your wiki.
Use the ingest-video skill to transcribe the local file meeting.mp4 and create a wiki source note with keyframes and the full transcript.
High-intent search queries and answers about installing and using this skill.
To transcribe a local video file into a searchable wiki page, this Skill processes the media to extract timestamped text and scene-change keyframes. It outputs a structured wiki source note containing the transcript, speaker labels, and embedded screenshots.
The best way to convert recorded meetings into searchable transcripts is using a tiered transcription approach that supports local Whisper, OpenAI Whisper, or AssemblyAI. Diarization is applied where available to attribute text to specific speakers automatically.
Yes, you need FFmpeg installed to extract audio and keyframes from video files for transcription. The Skill relies on FFmpeg to capture scene-change screenshots and fallback I-frames, saving these assets directly into your vault.
Yes, you can use local Whisper for video transcription instead of paid APIs. The Skill uses a provider fallback system that prioritizes local Whisper, then falls back to the OpenAI Whisper API or AssemblyAI depending on availability.
Keyframe extraction for lecture videos works by detecting scene changes and capturing screenshots, with a fallback to I-frame extraction if needed. It caps the total keyframe count and saves the images into your vault assets for embedding in study notes.
When turning screen captures into wiki source notes, limitations include dependency on FFmpeg for media processing and variable diarization availability based on the active transcription provider. The post-extraction report details these constraints and the final keyframe count.
armoin2018Automate audio format conversion, extraction, and transcription with FFmpeg and Whisper.
praxstackTransform lecture transcripts into structured study notes with flashcards and revision plans.
MLMarioOrchestrate a multi-agent pipeline to ingest raw knowledge base materials into structured wiki pages.
lachlanchenConvert audio and video files into timestamped Markdown, TeX, and PDF reports.
