One episode upload → a complete show-notes page: description, timestamped highlights, people and resources mentioned, and pull quotes.
Files are encrypted
EXAMPLE
EPISODE-42.MP3 — PODCAST EPISODE
arrow_forward
EPISODE-42-SHOW-NOTES.MD
…so I picked up Deep Work and it changed…
## Highlights
[12:04] Why deep work beats long hours
episode-42-show-notes.md · four sections notes
What you get
check_circleAn episode description written to make someone press play
check_circleTimestamped highlights, with times taken from the transcript
check_circlePeople, books, tools, and links exactly as spoken — never a guessed URL
check_circle2-4 verbatim pull quotes ready for social posts
check_circleMarkdown and a formatted DOCX, both named after your episode
How it works
1Upload one episodeDrop in an audio or video file up to 500 MB — the episode export, or the raw video recording.
2We transcribe, then write the notesThe speech is transcribed on our own servers into timed segments, then a language model writes the show notes from that transcript — and only from that transcript.
3Download the show notesA Markdown file and a formatted DOCX, both named after your episode, with the same four sections in the same order every time.
Who uses this tool
PODCASTING
Notes for every episode, same day
Upload the export as soon as you stop recording and paste the notes into your host before the episode ships.
MARKETING
Pull quotes for promotion
Verbatim quotes from the episode, ready to drop into social posts and the newsletter.
INTERVIEW SHOWS
Guest episodes, documented
Every book, project, and link your guest mentions is captured exactly as they said it.
AGENCIES
Show notes as a service
Producing several client shows? Turn each episode around without a writer scrubbing the audio.
EDUCATION
Lecture and seminar recaps
Recorded sessions get a description, highlights, and a reading list from what was actually cited.
CREATOR ECONOMY
Video episodes too
Upload the video recording — we extract the audio and write the notes from the speech.
SECURITY
Built for sensitive documents
Bank statements, medical files, case records. Security isn't a feature we added — it's the foundation.
lock
Encrypted in transit
Encrypted in transit over TLS 1.2+, and stored in access-controlled, encrypted object storage. Files are protected the moment they leave your browser.
admin_panel_settings
Your files stay yours
Workspaces are isolated per account. Role-based access shows teammates only what they need.
auto_delete
Deleted, not stored
Files are deleted after processing. Everything runs on our own hardware and is never sent to an outside AI service, so your data is never used to train models.
dnsProcessed on our own hardwareauto_deleteDeleted after processinglockEncrypted in transit
Questions
Common audio and video recordings: MP3, M4A, WAV, AAC, FLAC, OGG, OPUS, WMA, and video like MP4, MOV, M4V, WEBM, MKV, and AVI. For video we extract the audio track first. One episode per job, up to 500 MB.
Always the same four sections: a 2-3 paragraph episode description, timestamped highlights in episode order, every person, book, tool, and link mentioned, and 2-4 verbatim pull quotes. Everything is written from the transcript — nothing is invented, and a section with nothing to report says so.
From the transcript itself. The speech is transcribed in timed segments, and highlight timestamps are taken from those segment markers — they are never made up. Timing is derived from speech chunks, not word-level, so a highlight points to the right stretch of the episode rather than the exact second a word is said.
It lists every resource exactly as it was spoken — if your guest says "my site, example dot com", that is what appears. It never guesses or completes a URL, so you may want to add the full links before publishing. There are also no speaker labels, so mentions are not attributed to host or guest.
6 credits per minute of audio. Because the length is not known until the file is processed, the upfront hold is estimated from file size at a typical bitrate for the format (about 1 MB per minute for MP3 audio, more for WAV, FLAC, or video). The minimum is 6 credits.
Yes. Episodes run on our own servers, are never used to train any model, and are auto-deleted 7 days after the job finishes.