Earkeep
Decide on evidence, not opinion, by keeping every session word for word
The moderated session, the debrief, the synthesis: research is only as good as the fidelity of what you kept. Earkeep is an always-on transcriber that keeps every session on your own device, with nothing new on the table and no bot in the call.
No bot · No cloud · No record button
14-day full trial, no account required.
The sessions that decide it
Moderated session
What has to survive it is a complete, timestamped transcript, because a highlight reel is only as traceable as the words underneath. In a meta-analysis of 28 studies, 15% of participants said a camera changed how they behaved.
With Earkeep: capture is already running, so there is no record button to press in front of the participant. Audio is transcribed on your device and never written to disk. How private-by-design works →
Note-taker debrief
What has to survive it is the first impression, in the minutes before the next session blurs it, when a cloud tool is still uploading.
With Earkeep: transcription is local as the day goes, so the debrief works from the real transcript. You mark session and debrief as their own spans. How always-on works →
Synthesis workshop
What has to survive it is the theme with the verbatim quotes attached. dscout puts synthesis at two to three hours per hour of interview, out of reach for most teams.
With Earkeep: transcripts are plain text files, so an agent can read a month of sessions and report what recurred or where participants contradicted each other. It is a reviewed first pass, not a verdict. How agents work in Earkeep →
The rest of the week
Those three are where the evidence is made, not where the week goes: eight 45-minute sessions can mean roughly eighteen hours of synthesis.
| Meeting | You | What has to survive it |
|---|---|---|
| Usability test session | Run | Failure moments, verbatim reactions, timestamps |
| Stakeholder readout | Run | A recommendation somebody will act on |
| Intake and scoping call | Run or attend | An agreed research question |
| Recruitment or screener review | Attend | A consented participant list |
| Research team or ops sync | Attend | Shared status, so no study runs twice |
| Cross-functional critique | Attend | Evidence for a decision already in motion |
| Diary study or field check-in | Run | Notes tied to the study timeline |
Every scheduled row above titles its own span from your calendar, so a seven-session week ends as named transcripts with no export step.
A moderated session already has a script, so most of this list needs no minutes template. The exception is the stakeholder readout, and the shape it wants is on the meeting minutes hub.
Further reading: open-ended questions, establishing rapport and empathic listening.
See it in action
A day of sessions, end to end
Scrub the day timeline to where a participant hesitated and read what they said.
Synthesis as a reviewed first pass
Point your own agent at a month of sessions and ask what recurred. You review a draft with the verbatim quotes attached, which keeps it checkable.
Pricing: one payment, no subscription
€39
once, for one device, not a subscription.
No tiers, no per-seat billing. Try it free for 14 days, no account required. See full pricing →
FAQ for UX researchers
Does Earkeep record participants without their knowledge?
No. It does not join calls or announce itself, and it does not replace informed consent: recording a participant, local or not, still requires telling them and getting their agreement.
Where does a participant's audio actually go?
Nowhere. Audio is processed only in memory and never written to disk or uploaded. Only the text transcript is saved locally.
Can I delete one participant's session without touching anything else?
Yes. Transcripts are plain files on your disk, organised by day and span, which you can edit or delete like any file.
Does this replace my research repository, like Dovetail or Condens?
No. Earkeep is the capture and transcription layer; synthesised findings still go into your repository.
Does Earkeep support the languages my participants speak?
Whisper covers 99+ languages and Parakeet-TDT v3 covers 25 European ones. Check yours in the full supported-language list.
Will always-on capture slow down my device during back-to-back sessions?
No more than a normal transcription app: transcription runs only when someone is speaking, so silence between sessions costs nothing extra.
Stop losing what participants said
14-day full trial, no account required.