Why MarkdownNodeParser changes the math on audio

Flat-text node parsing on transcripts loses everything that makes a conversation useful: who said what, when they said it, and where one topic ends. MarkdownNodeParser reads the structure the converter emits — ## speaker headings, ### topic subheadings — and builds a node tree that mirrors the conversation's real shape.

Retrieval over that tree gets two superpowers immediately. Auto-merging-retriever can climb from a specific quote to the speaker's full turn to the topic section it belonged to. Hierarchical summary indexes can summarise per-speaker, per-topic, or per-time-window without re-chunking.

The workflow

Convert each recording on Audio to Markdown, save the .md files into an ingestion directory, load with SimpleDirectoryReader (filtered to .md), parse with MarkdownNodeParser. The same pattern works for podcast archives, meeting series, interview corpora — any time you have multiple structured transcripts to index together.