Extract and transcribe media content from URLs, local files, and streams.
npx skills add https://github.com/buildoak/fieldwork-skills --skill summarize-buildoak
Please help me install this Agent Skill. Skill: summarize Source: https://github.com/buildoak/fieldwork-skills/tree/main/skills/summarize Command: npx skills add https://github.com/buildoak/fieldwork-skills --skill summarize-buildoak
Extracts and transcribes media content from URLs, local files, and streams to provide reliable, machine-readable input for AI reasoning.
Provide a URL or local file path to extract and transcribe media content.
High-intent search queries and answers about installing and using this skill.
To extract text from YouTube videos or podcasts, provide the media URL to automate transcription. It uses yt-dlp to fetch content and Whisper or cloud backends to generate readable transcripts for downstream workflows.
Yes, you can use OCR to extract text from PDF files and images. The process relies on Tesseract and markitdown to perform image OCR and PDF preprocessing, converting visual media into machine-readable text.
Yes, ffmpeg and uv are required dependencies for transcribing local audio files. Ffmpeg handles media decoding while uv manages the Python environment, ensuring deterministic content loading for transcription.
The best way to transcribe streaming media into readable text is by providing the stream URL directly. The tool automates extraction and transcription, feeding the output directly into AI reasoning pipelines.
Yes, local transcription is supported without sending data to the cloud. By utilizing whisper-cli, media extraction and audio transcription can run entirely on your local machine, ensuring data privacy.
PDF text extraction requires markitdown and tesseract because they handle PDF preprocessing and optical character recognition. They convert complex visual document structures into plain text suitable for AI summarization.
RuifengFuExtracts text from Bilibili videos and subtitles using yt-dlp, ffmpeg, and faster-whisper ASR.
519labIndexes and searches markdown notes locally using BM25, vector search, vector search and LLM reranking.
steipeteTranscribe local audio files to text or subtitles using the Whisper CLI.
lenadlmExtract text from images using Tesseract and cloud OCR APIs.
