Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a study guide
Turn a recording into a study guide
A lecture is paced for a room. Revision needs it paced for one person, alone, later.
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.
Core conceptsDefinitionsWorked examplesSelf-check questions
Study guide
Material reorganized for retention: concepts, definitions, examples, self-checks.
Recorded teaching is optimised for the hour it was delivered in, which is why replaying it is such a poor way to revise. Ancher reorders the material for retention instead: the concepts in dependency order rather than delivery order, definitions taken from how the speaker actually explained them, the worked examples kept in full, and self-check questions built from what the room was genuinely confused about.
The honest version
What the room asked about is the syllabus of what is hard
Every recorded class contains a free difficulty survey: the questions people interrupted to ask. Those are the points where explanation failed for a real listener, which makes them the points worth testing yourself on. A transcript buries them in the middle of the hour. Working from the timeline, Ancher can pull them out and turn them into checks.
One second of one recording, at 33:05, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
so the coefficient here comes out at , which is the bit people always trip on
Slide on screen — not readThe specific never reaches the draft
Study guide
Slide on screen
β₁ = 0.62 (s.e. 0.11)
from 33:05
Lands in the draft, with its timecode
- Self-check questions are generated from what was actually asked in the room, not from what a summariser guessed was important.
- Concepts are ordered by what depends on what, so a later idea never arrives before the one it needs.
- Every worked example keeps its timestamp, so the moment you lose the thread you can hear it worked through again.
What comes out
Study guide, section by section
Material reorganized for retention: concepts, definitions, examples, self-checks.
Core concepts
The ideas in dependency order, each with why it matters rather than only what it is.
Definitions
Terms defined the way the speaker explained them, including the informal version that made it click.
Worked examples
Worked examples kept whole, because a truncated example teaches nothing.
Self-check questions
Questions built from where the room got stuck, with the timestamp of the answer.
Further reading
What was referenced in passing and is worth reading before the next session.
Recording-to-study-guide 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.
Turn this recorded session into a study guide. Order the concepts by dependency, not by when they were taught, and say why each matters. Define terms the way the speaker explained them, including the informal version. Keep worked examples complete with their timestamps. Build self-check questions from the questions the room actually asked, and list anything referenced in passing that is worth reading.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Transcript with timings | Worked examples | An example is only useful in full, and the timings are what let a long derivation be kept whole and still be navigable. |
| Unresolved threads | Self-check questions | A question asked and half-answered before the class moved on is the highest-value thing to test yourself on later. |
| Screen shares, if it is video | Definitions | The precise form of a definition is usually written on a slide and spoken loosely, so the frame is the more reliable of the two. |
| Duration and timeline | Core concepts | Minutes spent is a rough proxy for weight, which is a reasonable first guess at what the exam cares about. |
| Commitment language | Further reading | Read this before next week is an instruction that gets lost in an hour of audio and belongs in a list. |
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 study guide. Ancher fills core concepts, definitions, worked examples, self-check questions, further reading 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
- Guides that follow the lecture's running order recreate the problem. Revision needs dependency order, which is often close to reversed.
- Boards, gestures and anything pointed at are invisible to audio. If a session was heavily visual, the guide will have holes where the pointing was.
- Recording a class usually needs the institution's permission as well as the lecturer's, and the rules differ by jurisdiction.
Questions people ask
Where do the self-check questions come from?
Mostly from the questions the room asked. Those mark the places where an explanation failed for a real listener, which makes them far better test material than questions generated from the summary alone.
Does it work for a whole term of recordings?
Yes, and it works better. Put the term in one collection and a concept introduced in week two and assumed in week nine gets connected rather than defined twice, which is what a per-lecture guide cannot do.
What if the lecturer wrote on a board?
Board work only survives if the recording is video, where frames are sampled. Audio-only recordings of a visual class will have gaps, and the guide marks them rather than inventing the missing step.
Bring your own recordings
Everything you save lives in one workspace, so the study guide is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same study guide also comes from YouTube video, PDF, web page.