概要
Streamlines the data preparation phase of qualitative research by automating the transcription of audio files and the conversion of complex documents into analyzable markdown. It features a tiered capability system that leverages MinerU for high-accuracy VLM-powered PDF parsing and table extraction, or utilizes bundled tools for standard audio-to-text workflows. By organizing output into a standardized directory structure and maintaining a central data inventory, it ensures research data is consistent, searchable, and ready for deep interpretive analysis.
