Tota is a Mac app that transcribes research interviews with speaker labels and lets you draft by voice, with all processing on your Mac, so participant data stays where your ethics approval said it would.
Your ethics application said participant recordings would be stored on an encrypted university device and not shared with third parties. Then the transcription backlog hit thirty hours and the cloud services started looking tempting. Tota transcribes the recordings on your Mac, labels speakers, exports with timestamps, and costs £19.99 once rather than a per-minute fee that scales with your sample size.
Why cloud transcription conflicts with your ethics approval
Most ethics approvals and data-management plans commit the researcher to keeping identifiable participant data on approved, encrypted storage and not disclosing it to third parties without a specific agreement. Uploading recordings to a cloud transcription service is exactly that disclosure, and the service's terms about retention and model training rarely match what the committee was told.
Transcribing by hand honours the commitment and takes four to six hours per interview hour. The alternative is a transcription tool that runs entirely on the researcher's own machine. Apple Silicon Macs can run OpenAI's Whisper models locally, with on-device speaker identification, fast enough to clear a backlog in an afternoon.
Tota is that tool, plus system-wide dictation for the writing. Audio Drop transcribes files on the Mac with speaker labels and timestamps; the dictation side types field notes, memos and drafts into NVivo, Word, Obsidian or anywhere else. No account, no upload, no per-minute charge.
What researchers actually transcribe and dictate
- Semi-structured interviews. Dropped onto Audio Drop; speakers labelled automatically and renamed to participant codes.
- Focus groups. Multi-speaker recordings where diarisation does the first pass at who said what.
- Field notes and reflexive memos. Spoken straight after an observation, while it is still accurate.
- Drafts, abstracts and reviewer responses. Dictated into Word, Google Docs or a LaTeX editor, then edited.
- Lecture notes and feedback to students. Short writing that is faster to say than type.
What leaves your Mac, and what doesn't
This is the whole list. Every row is checkable from the app's own behaviour, and the security page explains how to watch its network activity yourself.
| Data | Leaves your Mac? | What actually happens |
|---|---|---|
| Your voice while dictating participant data and field notes | No | Recorded to a temporary file, transcribed on your Mac by Whisper via WhisperKit, then deleted. |
| The transcript | No | Typed into the app you are using. Kept in a local history for three days, then archived as Markdown in a folder you choose. Entries can be deleted. |
| Text on your screen | No | With “Spell what’s on your screen” on, the visible text of the window you are dictating into is read once, to bias spelling. Never stored or sent. Can be turned off. |
| Glossary terms and learned corrections | No | Stored as JSON files in Tota’s folder in Application Support. |
| Smart Formatting | No | Runs a local Qwen 3 language model via MLX. Off by default. |
| Audio files dropped in for transcription | No | Transcribed and speaker-labelled on your Mac. |
| Licence key and a machine identifier | Yes | Sent to api.lemonsqueezy.com at activation and validation. Never any content. |
| Update check | Yes | A download request to github.com at launch. Can be disabled in Settings. |
| Model downloads | Yes, one-way | Speech, formatting and speaker-ID model files from huggingface.co, once, on first use. |
| Usage analytics or crash reports | Never | There is no analytics or crash-reporting SDK in the app. |
How Tota works for researchers and academics
Install the app, grant it microphone and accessibility access, and press Cmd+Shift+R wherever your cursor is. Tota records until you press it again, transcribes the audio on your Mac with OpenAI's Whisper model running through WhisperKit, and types the result into the field. There is also a hold-to-talk key for short entries and a “Hey Tota” wake word for hands-free use. It behaves like a keyboard, so it works in browser-based systems, Word, email, Notes and anything else with a text field, with no integration to request from IT. After the one-time model download it needs no internet at all.
Three optional layers sit on top. Smart Formatting runs a small local language model that fixes punctuation, turns “new paragraph” and “new list” into structure, and corrects stutters without rewriting what you meant. The auto-learning dictionary remembers the corrections you make. And Audio Drop transcribes audio files you already have, with automatic speaker labels, also on-device.
Workflows for a research project
- The interview transcript. Drop the file on Audio Drop, rename 'Speaker 1' to the participant code, export Markdown or plain text for NVivo, ATLAS.ti or MAXQDA. SRT or JSON give you timestamps for quotations.
- A glossary per study. Put the study's key terms, place names and pseudonyms in a glossary so memos and drafts spell them correctly. Glossaries bias dictation only; check names in an Audio Drop transcript against the audio.
- Reflexive memos by voice. Use the 'Hey Tota' wake word for hands-free memos after fieldwork, with the text going into your notes app.
- Writing up. Dictate the draft, edit on screen. Filler-word removal and Smart Formatting keep the text clean without rewriting your meaning.
A glossary for researchers and academics
Every discipline has vocabulary that general speech recognition mishears. A Tota glossary is a short list of terms the speech model is nudged towards while it transcribes, with sound-alike matching afterwards for anything it still mishears. A glossary for a qualitative study might hold:
- participant pseudonyms and codes
- the study's key constructs
- place and organisation names
- methodology terms such as 'thematic analysis' or 'grounded theory'
- software names such as NVivo, Zotero and R
- names of authors you cite often
The live hint has room for roughly 70 to 90 words, so one glossary per study works better than one for the whole department. Tota can switch glossary by app.
The glossaries guide covers set-up, the hint budget and per-app switching.
What Tota does not do
- It is not a qualitative-analysis tool. Tota produces transcripts. Coding, themes and analysis happen in NVivo, ATLAS.ti or wherever you do them.
- Transcripts need checking. Whisper is accurate but not perfect, and speaker labels can need correcting in crosstalk. Timestamps exist so you can verify against the audio.
- It does not record. Record with your usual consented method and transcribe the file. Tota does not capture Zoom or Teams calls itself.
- Transcripts are files on your Mac. Nothing is synced or backed up by Tota. FileVault, your backup tool and your device policy are what protect them.
Pricing for a research group
Tota is a one-time purchase of £19.99, with two seats per licence, after a 14-day free trial of every feature. There is no subscription, no per-minute transcription fee and no word limit, because local processing costs us nothing per word. Larger teams buy additional licences. Pricing is the same worldwide; see the pricing section for what the licence includes.
Frequently asked questions
Are participant recordings uploaded anywhere?
No. Audio Drop transcribes files on your Mac using OpenAI's Whisper via WhisperKit, and speaker identification runs on-device too. Nothing is sent to a server. The only network calls are a licence check, an update check and one-time model downloads.
Can I state this in a data-management plan?
Yes. Tota performs all transcription on the local device and transmits no audio or text; the security page enumerates every network call so a reviewer can verify it. The transcripts are ordinary files under whatever encryption and storage policy your institution requires.
Are there minute limits or per-interview fees?
No. Tota is a one-time £19.99 purchase with unlimited transcription. A thirty-hour backlog costs the same as a thirty-minute one.
Does it export to a format NVivo or ATLAS.ti can import?
Yes. Exports include plain text, Markdown, SRT, JSON and CSV. Plain text with speaker labels imports into the major qualitative-analysis packages.
Does it handle other languages?
Whisper's multilingual models transcribe many languages and can translate into English. Choose a multilingual model in Settings.
Can my co-investigator use the same licence?
Each licence includes two seats, so two Macs can be activated.
Clear the transcription backlog on your own Mac
Download Tota and drop the first interview on it. No per-minute fee, nothing uploaded. Two seats, £19.99 once.
14-day free trial · macOS 14 or later · No account needed
