Audio to Markdown for Logseq: Voice Notes as Outlines
Logseq is outline-first: every line is a referenceable block with its own UUID. Most transcription tools produce flat prose blobs that Logseq treats as one long paragraph. Convert audio with structured Markdown output and the same content becomes a proper outline: each topic section is a block you can [[link]] to, ((reference)) from anywhere, and surface in graph view.
How Logseq stores transcripts as Markdown
Logseq watches its pages/ directory for .md files. Drop a converted transcript there (named 2026-02-14 Pricing Discussion.md or whatever convention you use), and Logseq parses every block into a discrete UUID-tagged unit. Topic headings become block-level headings, and the paragraphs under each become child blocks. From that point you can [[wikilink]] to the page, ((block-ref)) to a specific quote, or query across with Datalog.
The "voice memo to journal" workflow
Record a voice memo, convert on Audio to Markdown, save into pages/. From your Logseq journal entry for the same day, embed the page ({{embed [[2026-02-14 Pricing Discussion]]}}) or block-reference specific moments (((block-uuid))). The journal stays focused on your thoughts; the source transcript lives in its own page; references connect them with full context.
Splitting long meetings for Logseq performance
Logseq performs best with smaller pages: multi-thousand-block transcripts make the outliner sluggish. For meetings over an hour, split by major topic (use the structured Markdown's ### topic headings as natural cut points), one page per topic, all linked from a parent index page. The graph view then shows the meeting as a small cluster of connected pages instead of one giant node. Pair with PDFs (PDF for Logseq) and web sources (URL for Logseq) for a full-spectrum knowledge graph.
Frequently asked questions
How does Logseq handle Markdown imported from audio transcripts?
Identically to any other Markdown: Logseq watches pages/ for .md files and parses each into its block graph. A converted transcript, dropped into pages/, becomes immediately searchable, referenceable, and linkable from anywhere in your graph. Each paragraph gets its own UUID for granular block references.
Can I block-reference specific moments from a meeting transcript?
Yes: every block in a Logseq page has a UUID. Hover over the block to see the reference syntax (((uuid))). Paste that reference into any other page or journal entry, and the original block content renders inline. Useful for citing specific quotes from a meeting in unrelated project notes.
Should I split long transcripts into multiple Logseq pages?
For transcripts over 3000-5000 words, yes. Logseq performs better with smaller pages, and the outliner UX gets unwieldy on multi-thousand-block pages. Split by topic (use ### headings from the converter as cut points), one page per topic, all linked from a parent index page that maps the meeting structure.
How do I tag transcripts for cross-meeting queries?
Logseq treats #tag mentions as block-level tags. Add tags either at the top of the transcript page (#meeting #pricing #2026-q1) or per relevant block (tag a specific decision with #decision, a specific commitment with #commitment). Datalog queries can then surface all decisions across all meetings, all commitments by participant, etc.
Can I query transcripts with Datalog?
Yes: Logseq queries treat transcript content the same as hand-written content. Useful pattern: tag each transcript with the meeting series (#standup, #kickoff), then query for all blocks across all standups containing a specific phrase or tag. Combined with simple {{query}} blocks, you can build dashboards over your entire meeting history.