How can transcription work without a server?

The browser downloads OpenAI's Whisper speech model once (about 75 MB) and runs it locally using WebGPU — your graphics hardware. On iPhone, the same model family runs on the Neural Engine. Modern devices transcribe faster than real time, so the text streams live while you speak.

Is the transcription accurate without the cloud?

It's the same Whisper model family that many cloud services run server-side — published benchmarks put whisper-small within a couple of WER points of commercial cloud ASR on meeting audio. A higher-accuracy on-device pass can re-process the recording after you stop.

Where are my recordings stored?

In your browser's local storage (IndexedDB) on your device, or in the iOS app's local storage. They never upload. Pro can back up the meeting text — title, transcript, summary — to your account; the audio stays local even then.

Do AI summaries break the privacy model?

Summaries are optional and text-only: clicking Summarize sends the transcript text (never audio) to an LLM. If your content is too sensitive even as text, don't use the button — recording, transcription, and speaker labels all work without it.

What about languages other than English?

Live on-device transcription supports 29 languages. English is the most accurate; major European and Asian languages work well on the high-accuracy setting.

private meeting transcription — your audio never uploads

now recording transcribes meetings entirely on your device: the Whisper speech model runs inside your browser (or on your iPhone's Neural Engine), so the audio is converted to text locally and is never uploaded, stored, or processed on a server. You can verify this yourself in the browser's DevTools network tab while recording. The only data that can ever leave the device is text — an AI summary you explicitly request, or Pro cloud sync of meeting text.

Updated 2026-06-12 · by the now recording team

Free, in your browser, no account needed — and your audio never leaves your device.

Record a meeting free

Where your meeting audio actually goes

	Cloud transcription (Otter, Fireflies, Notta)	Bot-free + cloud AI (Granola, Fathom)	now recording
Audio uploaded to vendor servers	Yes	Yes (for AI processing)	Never
Audio stored by the vendor	Yes (retention policies vary)	Varies	Never — it never arrives
Transcription location	Vendor cloud	Vendor cloud	Your device (Whisper on WebGPU / Neural Engine)
Can be used to train models	Per their policy	Per their policy	Impossible — no audio to train on
Subject to vendor breach	Yes	Yes	No audio to breach
Works offline after first load	No	No	Yes — transcription is local
Provable from your side	No	No	Yes — DevTools network tab

who actually needs on-device transcription

Most note-taking tools optimize for convenience and treat audio as something to ship to a data center. That trade is unacceptable in a lot of real work: attorney–client conversations, therapy and medical consultations, HR investigations, journalism with confidential sources, M&A and board discussions, security reviews, and any meeting covered by an NDA that doesn't have a "we may share recordings with our AI vendor" carve-out.

For all of these, the cleanest answer to "is the vendor's cloud secure enough?" is to make the question disappear: if audio never leaves the machine, there is no vendor cloud to evaluate, no retention policy to negotiate, and no breach scenario that includes your recordings.

what this means for GDPR and compliance

This is not legal advice, but the structural difference matters for compliance reviews: with cloud transcription services, the vendor processes your meeting audio, which typically makes them a data processor and triggers DPA, sub-processor, and data-residency questions. With on-device transcription there is no audio processing relationship at all — the recording and transcript live in your browser's local storage, on hardware you already control.

Two optional features do send data, and both are text-only and explicit: AI summaries send the transcript text to an LLM when you click Summarize (free plans include 10 a month), and Pro cloud sync backs up meeting text — never audio — to your account. Both are skippable; the recorder works fully without them.

verify it in 10 seconds

Open nowrecording.com, press F12 to open DevTools, and select the Network tab. Start a recording and talk. You'll see the speech model download to your device (one time, cached afterwards) — and no audio leaving it: no WebSocket streams, no chunked uploads, nothing. Stop the recording and the transcript is already there, because it was produced on your machine while you spoke.

The honest verdict

If your meetings could appear in a compliance review, a court filing, or a journalist's source-protection plan, transcription that physically cannot upload audio is the only category that removes the risk instead of managing it. now recording is the zero-install way to get it: free in the browser, verifiable in DevTools, with text-only cloud features that stay opt-in.

frequently asked questions

How can transcription work without a server?: The browser downloads OpenAI's Whisper speech model once (about 75 MB) and runs it locally using WebGPU — your graphics hardware. On iPhone, the same model family runs on the Neural Engine. Modern devices transcribe faster than real time, so the text streams live while you speak.
Is the transcription accurate without the cloud?: It's the same Whisper model family that many cloud services run server-side — published benchmarks put whisper-small within a couple of WER points of commercial cloud ASR on meeting audio. A higher-accuracy on-device pass can re-process the recording after you stop.
Where are my recordings stored?: In your browser's local storage (IndexedDB) on your device, or in the iOS app's local storage. They never upload. Pro can back up the meeting text — title, transcript, summary — to your account; the audio stays local even then.
Do AI summaries break the privacy model?: Summaries are optional and text-only: clicking Summarize sends the transcript text (never audio) to an LLM. If your content is too sensitive even as text, don't use the button — recording, transcription, and speaker labels all work without it.
What about languages other than English?: Live on-device transcription supports 29 languages. English is the most accurate; major European and Asian languages work well on the high-accuracy setting.

try it on your next meeting

Free, in your browser, no account needed — and your audio never leaves your device.

Record a meeting free