Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a blog post
Turn a recording into a blog post
Speech repeats itself on purpose. The repetition is where the argument is hiding.
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.
The angleOpeningBody sectionsSpecifics and numbers
Blog post
A publishable article with its own argument, not a transcript rearranged into paragraphs.
Nobody speaks in paragraphs, so a recording turned into prose sentence by sentence reads like a person being transcribed rather than a writer making a case. Ancher works from the whole timeline instead: the claim a speaker returned to three times becomes the angle, the number they said once becomes the evidence, and the aside they never finished becomes a line the draft has to either answer or drop.
The honest version
The thing said three times is the argument; the thing said once is the proof
A speaker circles. They state a position early, wander, restate it harder, then land on it at the end — and somewhere in the middle they drop a single number that makes the whole thing credible. A transcript flattens all of that into equal lines. Ancher keeps the timeline, so repetition across it is visible as repetition, and the one-off specific is visible as the specific.
One second of one recording, at 18:47, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
and honestly the churn number is the whole story here, it's now
On the shared screen — not readThe specific never reaches the draft
Blog post
On the shared screen
Monthly churn 3.1% → 1.4%
from 18:47
Lands in the draft, with its timecode
- Recurrence across the timeline is what nominates the angle, rather than whatever was said first.
- A figure spoken once still carries the second it was said at, so the draft can cite it instead of paraphrasing it away.
- If the recording is video, a number that only appeared on the shared screen is still available to the paragraph that needs it.
What comes out
Blog post, section by section
A publishable article with its own argument, not a transcript rearranged into paragraphs.
The angle
The position the speaker kept returning to, stated as a claim a reader could disagree with.
Opening
An opening built from the moment the recording actually got interesting, which is rarely the first minute.
Body sections
Sections in the order that argues best, not the order the conversation happened to wander through.
Specifics and numbers
The figures and examples spoken aloud, each still attached to the second it was said.
Sources and credit
What the recording was, when it happened, and who is being quoted.
Recording-to-blog-post 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.
Write a blog post from this recording. First identify the claim the speaker returned to most across the timeline and state it as the angle. Open at the moment the recording became interesting, not at the beginning. Order the body for argument rather than chronology. Attach the second to every figure or example you use, keep hedged numbers hedged, and close with what the recording was and who is quoted.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Transcript with timings | Specifics and numbers | Start and end seconds on every segment are what let a published claim be checked against the audio in one click. |
| Duration and timeline | The angle | How long a speaker stayed on a subject is the closest thing a recording has to emphasis, and emphasis is what nominates the angle. |
| Unresolved threads | Body sections | A thought the speaker abandoned mid-sentence is a section the draft either has to finish properly or leave out. |
| Screen shares, if it is video | Specifics and numbers | On a video call the decisive number is often only on the shared screen, never spoken, and the paragraph still needs it. |
| Commitment language | Opening | The sentence where somebody committed to something is usually the moment the room woke up, which makes it a better opening than the agenda. |
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 blog post. Ancher fills the angle, opening, body sections, specifics and numbers, sources and credit 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
- Publishing a recording as prose is the failure mode, not the goal. If the draft still has the speaker's filler rhythm in it, the angle was never found.
- Anything you quote from a conversation needs the speaker's agreement before it goes out, and that is a separate conversation from the one about recording.
- Speech is loose with numbers — roughly, about, something like. Loose in speech becomes false in print, so a hedged figure has to stay hedged.
Questions people ask
Will it just be the transcript with headings?
No, and that distinction is the whole point of the route. The transcript is the input; the draft is reordered around an argument, which usually means the last ten minutes of the recording end up near the top.
How do I check a quote before publishing?
Every line carries the second it was said at, so you play that second. It takes about as long to verify a quote as it does to read it, which is the only reason quote-checking actually happens.
What if two people are talking?
You will get what was said and when, but not who said it, so any attributed quote needs you to confirm the speaker by listening. For a single-voice recording this is a non-issue.
Bring your own recordings
Everything you save lives in one workspace, so the blog post is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same blog post also comes from YouTube video, PDF, X thread.