Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a mind map
Turn a recording into a mind map
Conversations wander back to the same three things. A map makes that visible.
Free to try, no card. Your recording opens in Ancher.
Transcript with timingsCommitment languageUnresolved threads
Kept in parts
Every one of these stays separately addressable instead of collapsing into one block of text.
CentreBranchesCross-linksGaps
Mind map
The structure of an argument, laid out so the shape is visible at a glance.
A discussion moves in one dimension, so the fact that a subject came up at minute four, minute nineteen and minute fifty-one is invisible while you are in it. A map collapses the timeline into structure: the branches that took real time, the links between subjects the room kept accidentally connecting, and the branch that was raised twice and never developed.
The honest version
The branch nobody finished is as informative as the ones they did
On a map, a stub is visible. A subject raised twice and abandoned twice sits there as a short branch with nothing under it, and that shape is the useful part — either it does not matter, or it matters and the room keeps avoiding it. In a transcript that pattern is spread across an hour and reads as nothing at all.
One second of one recording, at 51:03, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
and that's the problem again, which we keep circling back to
On the shared screen — not readThe specific never reaches the draft
Mind map
On the shared screen
Raised at 04:11 · 19:26 · 51:03
from 51:03
Lands in the draft, with its timecode
- Branch size follows the time actually spent, so the map shows the discussion's real weighting rather than the agenda's.
- Subjects the conversation kept connecting become explicit cross-links instead of coincidences.
- Anything raised and dropped is drawn as an unfinished branch and labelled as one.
What comes out
Mind map, section by section
The structure of an argument, laid out so the shape is visible at a glance.
Centre
What the conversation was actually about, which is not always what it was scheduled to be about.
Branches
Main subjects, sized by the time they took.
Cross-links
Cross-connections the conversation made repeatedly without naming them.
Gaps
Branches raised and never developed, marked as unfinished.
Legend
How to read the map, including where the timestamps sit.
Recording-to-mind-map prompt
The link on its own gets a summary. This is the instruction that produces the 5 sections above, in that order, with the rules that keep them honest. Paste it with your recording — in Ancher, or in whatever assistant you already use.
Map this recording. Put what the conversation was actually about at the centre, which may not be the agenda. Draw main branches sized by the time each subject took. Add cross-links where the discussion repeatedly connected two subjects without naming the connection. Mark anything raised and never developed as an unfinished branch, keep timestamps on the nodes, and stay within two levels of depth.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Duration and timeline | Branches | Minutes per subject is the only honest weighting a recording offers, and it is what branch size should follow. |
| Unresolved threads | Gaps | An unfinished branch is a visual object; the same thing in a transcript is a sentence nobody rereads. |
| Transcript with timings | Legend | Timestamps on nodes are what let a map be a navigation surface for the recording rather than a picture of it. |
| Commitment language | Cross-links | Where a commitment ties two subjects together, that is a real dependency and belongs as a link rather than as two separate nodes. |
| Screen shares, if it is video | Centre | Whatever stayed on the shared screen longest is usually the true centre, whatever the agenda claimed. |
Everything Ancher keeps from a recording
Transcript with timings
Every segment carries start and end seconds, which is what turns a claim into a record.
Commitment language
I'll take that, by Friday, let's park it — these phrases are what separate a task list from a topic list.
Unresolved threads
What a conversation failed to close is usually the reason for the next one.
Screen shares, if it is video
A shared screen is sampled as frames, so the number that drove a decision stays attached to it.
Duration and timeline
Where the time actually went is a finding in itself for any recurring meeting.
The four steps
- Add the recording. Upload the audio or video file. Ancher transcribes it and keeps a start and end time on every segment, so any line in the output can be traced back to the moment it was said.
- Nothing gets flattened. Transcript with timings, commitment language, unresolved threads, screen shares, if it is video, duration and timeline stay separately addressable instead of collapsing into one block of text.
- Ask for a mind map. Ancher fills centre, branches, cross-links, gaps, legend using the mapping above, not a generic summary pass.
- Check it before you use it. Every specific keeps a link back to where it came from in the recording, so a claim can be verified without reopening the source.
Where this goes wrong
- A map is a navigation aid, not a record. Decisions and owners belong in notes; putting them on a map is how they get lost.
- Long recordings produce maps too dense to read. Two levels of depth is usually the limit before the shape stops being visible.
- Time spent is a proxy for importance, not a measure of it. A subject settled in ninety seconds may be the most consequential thing in the hour.
Questions people ask
Why size branches by time?
Because it is the one weighting a recording actually contains. It is imperfect — quick decisions can be the most important — but it is honest, and it makes the difference between the agenda and the real discussion visible.
Can I jump from the map to the audio?
Yes, nodes carry timestamps. That is what makes the map worth having: it is a way into a long recording rather than a picture to look at once and close.
Does it work across several recordings?
Yes, and the gaps section gets sharper. A branch that stays unfinished across four weekly recordings is a much stronger signal than one abandoned in a single conversation.
Bring your own recordings
Everything you save lives in one workspace, so the mind map is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same mind map also comes from YouTube video, X thread, LinkedIn post.