Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a slide deck
Turn a recording into a slide deck
The talk already has a shape. Slides should carry it, not repeat it.
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.
Narrative arcSlide-by-slideData slidesAppendix
Slide deck
A paced presentation: one argument per slide, built to be talked over.
A deck built from a recording usually fails by putting the speaker's sentences on the slides, which leaves the presenter reading aloud what the room has already finished reading. Ancher splits the two apart: the argument becomes the slide sequence with one point each, the sentences that actually explained it become speaker notes, and the numbers keep the timestamps that let you check them before you stand up.
The honest version
Slides get the point; the spoken sentence becomes the note underneath it
The recording contains both halves of a presentation and they belong in different places. What was said is the note. What it amounts to is the slide. Keeping the timeline lets Ancher separate them properly — so a slide holds one claim, and underneath it sits the phrasing that made a real room understand it.
One second of one recording, at 15:52, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
and that took us from where we were to in a single quarter
Chart on the shared screen — not readThe specific never reaches the draft
Slide deck
Chart on the shared screen
Q2 retention 71% → 84%
from 15:52
Lands in the draft, with its timecode
- One claim per slide, with the sentence that landed it kept as the speaker note rather than as the slide text.
- Data slides carry the timestamp of where the figure was said or shown, so it can be checked before it is presented.
- What was raised but never resolved goes to the appendix, which is where the hard question in the room will send you anyway.
What comes out
Slide deck, section by section
A paced presentation: one argument per slide, built to be talked over.
Narrative arc
The arc the talk actually followed, stated in a few lines before any slide exists.
Slide-by-slide
One claim per slide, in the order that argues rather than the order that happened.
Data slides
Figures with the second they came from, spoken or on screen.
Appendix
The unresolved and the detailed, held back for questions.
Speaker notes
What to say under each slide, taken from what was actually said.
Recording-to-slide-deck 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.
Build a slide deck from this recording. Describe the narrative arc first, based on where the time actually went. Then give one claim per slide in argument order, not chronological order. Put the sentence that explained each claim into the speaker notes rather than onto the slide. Attach timestamps to every figure, and move anything raised but unresolved into the appendix.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Duration and timeline | Narrative arc | Where the minutes went in the recording is the arc the talk already had, and it is usually better than a reconstructed one. |
| Transcript with timings | Speaker notes | Speaker notes work best as the phrasing that already succeeded with a live room, which the timings let you keep intact. |
| Screen shares, if it is video | Data slides | Charts shown during the recording are the data slides, and the frame is what stops them being redrawn from a paraphrase. |
| Unresolved threads | Appendix | Whatever the room raised and left hanging is what the next room will ask, so it belongs behind the last slide. |
| Commitment language | Slide-by-slide | The moment someone committed to a course of action is the decision slide, and decks routinely bury it. |
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 slide deck. Ancher fills narrative arc, slide-by-slide, data slides, appendix, speaker notes 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
- Slides that reproduce spoken sentences make the presenter redundant. If a slide can be read aloud verbatim, the split between slide and note has not happened.
- An hour of talk is not an hour of deck. Most recordings support twelve to fifteen slides, and forcing more produces a document nobody presents.
- Figures that were only ever spoken can be misheard. Anything on a data slide should be checked at its timestamp before it goes in front of a room.
Questions people ask
How many slides from an hour?
Usually twelve to fifteen. An hour of speech contains far less argument than it feels like, and a deck that stretches past that is padding out slides nobody would present.
Where do the speaker notes come from?
From what was said. The phrasing that made a live room understand something is better than anything written cold afterwards, so it goes under the slide rather than on it.
What if the numbers were only on a shared screen?
They are still available if the recording is video, since frames are sampled. That is often how the data slides get built — the decisive chart was shown and described loosely, never read out.
Bring your own recordings
Everything you save lives in one workspace, so the slide deck is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same slide deck also comes from YouTube video, X thread, LinkedIn post.