Transcribes webpages, YouTube videos, and PDFs for use with Large Language Models.
Facilitates interaction between Large Language Models (LLMs) and online content by providing an MCP server that extracts and transcribes text from webpages, YouTube videos, and PDFs. It enables LLMs to process and understand information from various online sources by simply providing the URL.
主な機能
01Converts PDF files to markdown text
02Transcribes YouTube video content
03Extracts text content from webpages
043 GitHub stars
ユースケース
01Processing and understanding information contained within PDF documents using LLMs.
02Allowing LLMs to summarize YouTube videos.
03Enabling LLMs to answer questions based on webpage content.
