For UX, qualitative & academic researchers

Interview transcription that survives the IRB.

Quietly runs on your Mac. Plain-Markdown notes in a folder you pick. Nothing uploaded to OpenAI, Otter, or anyone else. The same words your consent form already says.

Download for Mac For your IRB
Free 7-day trial On-device Whisper 99 languages $49 once
What you get
Interview folders, anonymisable.

Plain .md, front-matter has participant ID, date, duration. Atlas.ti / Dedoose / NVivo all read it.

Local · No cloud
P07-2026-04-22.md 58 min · KR
P08-2026-04-23.md 42 min · EN
P09-2026-04-25.md Transcribing
The friction

Cloud transcription tools and IRB protocols don’t mix.

Whisper API and Otter ship audio off-device. Both go to OpenAI / Otter servers. IRB blocker on most studies that touch identifiable speech.

Rev human transcription is $1.50/min. Accurate, but a 60-min interview is $90, and your audio still leaves your laptop.

Self-hosting Whisper is a CLI weekend. Half-named files, no metadata, no batching, no front-matter. Then participant 14 sends an .m4a and the pipeline breaks.

Dovetail and Reduct charge cloud-tier prices to host data your IRB already cleared to keep local. You’re paying to add risk.

Why Quietly fits

The boring local-first pipeline you wished existed.

On-device

Audio + transcript stay on your Mac.

Whisper large-v3 transcribes locally; the audio file is deleted unless you keep it. Nothing leaves the device — the sentence your consent form already says.

Markdown

Open in Atlas.ti, Dedoose, or NVivo.

Front-matter has participant ID, date, duration. Body is clean, LLM-polished Whisper output. Easy to anonymise, easy to import, easy to cite.

Any audio file

Transcribe existing recordings, no CLI.

Pick Transcribe a file… and choose any common audio or video file (.m4a, .wav, .mp3, .mp4, …). Each becomes a Markdown note. No Python env, no GPU drivers.

99 languages

Korean & English, side by side.

Whisper auto-detects language per recording. Code-switching interviews (KR + EN) stay coherent — large-v3 handles them well. Tested daily on Korean academic interviews.

In-person

Lab interviews, fieldwork, intercepts.

Mic-only mode for in-person. Open Quietly and hit ⌘R to start a recording — no laptop full-screen, no awkward bot in the room.

$49 once

Doesn’t need a budget line.

One-time license. Cheaper than three hours of Rev. Approve once, use it for the whole dissertation.

For your IRB

The sentence you can paste straight into your protocol.

Designed to read identically to the privacy clause your IRB already accepts.

Audio recordings will be transcribed using OpenAI Whisper running locally on the researcher’s device (Quietly, meetquietly.com). No audio or transcript will be transmitted to a third-party server. Recordings will be deleted after transcription; anonymised transcripts will be retained for analysis.

We’re happy to provide a one-page technical brief for your IRB. Email support@meetquietly.com.

Your analysis stack

It’s just Markdown — every QDA tool reads it.

Atlas.ti
Import as plain text. Quote-level coding works directly on transcript paragraphs.
.md / .txt
Dedoose
Upload Markdown — Dedoose treats each as a document for thematic coding.
.md
NVivo
Convert front-matter to NVivo classifications via a tiny script — examples on request.
.docx ←
VS Code · ripgrep
Tag, search, and pull quotes across the whole corpus — it’s plain Markdown.
folder
Pandoc / LaTeX
Convert quotes into your dissertation’s bibliography format with one script.
cli
FAQ

Things researchers ask first.

Is the Whisper model really running on my laptop?
Yes. Whisper large-v3 ships inside the app and runs against your local CPU/GPU. The audio file is processed on disk and never sent over the network. Outbound traffic is limited to one-time model downloads, update checks, license validation, and Google Calendar polling if you opt in — never audio or transcripts.
How accurate is local Whisper vs. Rev or human transcription?
For clean recordings (interview-grade mic, quiet room), Whisper large-v3 is comparable to professional human transcription on English and very strong on Korean. An on-device LLM cleanup pass then fixes fillers, false starts, and punctuation, so the transcript reads clean — comparable to a cloud service's, but with nothing leaving your Mac. For noisy fieldwork audio, expect a verification pass — but at $49 instead of $90/hour, the math works.
Can I diarize speakers?
Today Quietly splits the transcript into speaker turns — a new block each time the speaker changes — which works well for two-person interviews. Full per-speaker diarization (labeling each individual participant, robust for focus groups with 4+ people) is coming soon, alongside per-channel diarization for when you record each participant on a separate track.
What happens to the audio file?
By default, audio is deleted after transcription completes. You can keep it (per-recording or always) — it stays on your disk in the same folder, with a matching filename to the .md note.
Will my IRB ask for a SOC 2 report?
Some will. Quietly is local-first software — there's no service to audit. We provide a one-page technical brief that covers data flow, network calls, and where Whisper executes. Most IRBs accept it. For the strict ones, the brief notes that audio and transcripts never traverse the network — outbound traffic is limited to optional model downloads, update checks, and Google Calendar polling if you opt in.
Can I use this for clinical / IRB-restricted work?
Several research groups use Quietly for IRB-approved interview studies. We don't market as HIPAA-certified — that's a service-level claim and Quietly is a local app — but the data handling matches what most IRB protocols require: on-device, no third-party transmission, researcher-controlled retention.

Replace your transcription budget with $49.

Free 7-day trial · No account, no card. 7-day refund, macOS 13+. Approve once, use it for the whole dissertation.

$ 49 once · 2 Macs
Download for Mac

Less than 1 hour of human transcription