Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a podcast
Turn a recording into a podcast
An hour of talk becomes eight minutes worth listening to, or it stays an hour nobody plays.
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.
ScriptSegmentsVoiceLength
Podcast
A narrated version you can listen to instead of read.
Re-releasing a raw recording as an episode does not work, because the listener has none of the context the room had and none of its patience. Ancher writes a narrated version instead: an opening that gives the listener the stakes, segments that hold one idea each, and a script paced to be spoken rather than read, with every claim traceable to the second it came from.
The honest version
Written to be spoken, which means shorter sentences than a document
Text that reads fine on a page falls apart when read aloud: clauses stack up, and a listener cannot go back a line. The script here is built for the ear — one idea per sentence, the subject named again rather than pronouned, and a listener who joins late still knowing what is being discussed.
One second of one recording, at 37:22, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
the thing that actually moved the needle was , not the campaign
Shown while it was said — not readThe specific never reaches the draft
Podcast
Shown while it was said
Referral share of signups: 41%
from 37:22
Lands in the draft, with its timecode
- Every claim keeps the timestamp it came from, so anything narrated can be checked against the original audio.
- Segments run to a stated length, because an episode that overruns is one nobody finishes.
- What the recording left unresolved is narrated as unresolved, rather than tidied into a conclusion that was never reached.
What comes out
Podcast, section by section
A narrated version you can listen to instead of read.
Script
The full narration, written in sentences a person can say in one breath.
Segments
Each holding one idea, with a target duration.
Voice
Tone and pacing notes, including what to slow down for.
Length
Total runtime and where to cut if it needs to be shorter.
Source credit
What the source recording was, and who is quoted.
Recording-to-podcast 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 narrated episode script from this recording. Open by giving a listener who was not there the stakes. Break it into segments holding one idea each with a target duration. Write for the ear: one idea per sentence, repeat the subject rather than using pronouns, and avoid stacked clauses. Attach the timestamp behind each claim, narrate anything unresolved as unresolved, and credit the source and speakers.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Transcript with timings | Script | Timings behind each narrated claim are what let a producer verify a line without re-listening to the whole recording. |
| Duration and timeline | Segments | How long a subject ran in the original is a reasonable starting point for how long its segment should be. |
| Unresolved threads | Script | Narrating what was left open is more honest than manufacturing a conclusion, and it gives the episode somewhere to end. |
| Commitment language | Source credit | Where somebody committed to something on the record, the episode should say who and when, or not use it at all. |
| Screen shares, if it is video | Script | A figure that was only on the shared screen still needs to be spoken aloud in a narration, since a listener has nothing to look at. |
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 podcast. Ancher fills script, segments, voice, length, source 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 of other people, even narrated over, needs their agreement. Consent to record is not consent to release.
- Written-to-be-read sentences fail out loud. Anything with three clauses should be read aloud before it is recorded.
- Internal recordings assume shared context. A listener has none, so anything unexplained will simply be lost.
Questions people ask
Is this the original audio re-cut?
No, it is a script for a new narration. Raw meeting audio is unlistenable to anyone who was not there, and cutting it down does not fix the missing context — narration does.
How long should an episode be?
Usually six to ten minutes from an hour-long recording. An hour of conversation contains far less that a stranger needs to hear than it feels like from inside the room.
Can I check the script against the recording?
Yes, every claim carries its timestamp. For anything going out publicly that check is worth doing, since spoken figures are often rounded and a narrated version makes them sound precise.
Bring your own recordings
Everything you save lives in one workspace, so the podcast is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same podcast also comes from YouTube video, X thread, LinkedIn post.