Pepys

Article

Local vs Cloud Dictation

Every dictation app turns speech into text somewhere. Where that happens, and what else the app does online, decides the trade-offs.

Local dictation processes speech on your device, while cloud dictation sends audio or text to remote servers. Local systems can reduce cloud dependence and work offline once models are downloaded. Cloud systems can offer cross-device services, centrally managed models and lower hardware needs. Many apps are hybrid, choosing local or cloud per mode, so check each step.

Local, cloud and hybrid dictation: what each means

Turning speech into text takes a speech model. Where that model runs, and where the optional cleanup step runs, define the architecture. Speech recognition is only one step: an app can also check a licence, look for updates or send analytics without sending your audio anywhere.

  • Local (on-device) dictation: Microphone → local model → text → destination app. Speech recognition runs on your device and the model is stored there, so recognition needs no internet once the model is downloaded.
  • Cloud dictation: Microphone → network → cloud model → text → device. Audio goes to remote servers that run the model and return text, so a connection is required.
  • Hybrid dictation: Microphone → local or cloud model, depending on the mode → text. You or the app choose per mode, so the architecture depends on your settings.
Local, cloud and hybrid dictation compared
ArchitectureSpeech recognition runsFormatting and cleanup runsInternet required?Where the models liveWhat may still go online
LocalOn your deviceOn your device, or an optional cloud stepNot for recognition, once models are downloadedOn your device, after a downloadModel downloads, licence checks, update checks, optional analytics and any optional cloud features
CloudOn the vendor's or a provider's serversUsually on the same serversYesOn the vendor's serversAudio, text and context for processing, plus account and usage data
HybridOn your device or on servers, by modeLocal or cloud, by modeDepends on the modeOn your device and on serversWhatever the cloud modes send, plus the local list

Does local dictation mean private?

Not automatically. Local speech processing can reduce how much raw audio goes to a vendor's servers, which is a real difference. Privacy also depends on everything else the app does.

A cloud service is not automatically unsafe either. Vendors publish retention and training terms, and some offer settings that limit what is stored. The useful question is which steps leave your device, and what the vendor says happens to them.

  • Telemetry: an app may send usage or crash events, and whether they are opt-in or on by default differs by app.
  • Licensing: activating or checking a licence usually makes a network request, even in a local app.
  • Update checks: apps look for new versions online.
  • Accounts: sign-in ties usage to an identity, and some local apps need none.
  • Optional AI and cloud features: a local recogniser can pair with a cloud step that rewrites the text, which sends the text out.
  • The destination app: see the next section.

Local dictation does not make the app you are typing into local

Dictation architecture is separate from how the destination app handles your text. If a dictation app inserts text into Claude, ChatGPT, Gmail, Slack or Cursor, those apps may send that text to their own servers, under their own terms.

  • The dictation app decides where your speech is recognised and what else it sends.
  • The destination app decides what happens to the text once it is inserted: it may store, sync or send it to its own servers.
  • Check both. Read the dictation app's data-flow statements and the privacy terms of the app you dictate into.

Is local transcription more private?

For the recording itself, usually yes. Local transcription turns audio into text on your own device, so the recording is not uploaded to a server to be transcribed. That removes one exposure, not all of them. The app can still go online for models, licences, updates or optional cloud features, and you are responsible for storing and securing the files.

Built-in operating-system dictation can be mixed: it may process some languages on the device and send others to the vendor's servers, so check its settings for your language.

Pepys makes one product of each kind, and they handle your words differently. Pepys Transcribe is cloud software for recordings you upload. Pepys Dictate is a Mac app for live dictation and for files and memos transcribed on the Mac.

Neither approach suits everyone. A cloud service can offer sharing, AI summaries and access from any browser; a local app keeps the audio on one machine. For recordings that must stay confidential, see the guide to confidential transcription.

How Pepys Transcribe (cloud) and Pepys Dictate (local) handle recordings and text
TopicPepys Transcribe (cloud)Pepys Dictate (local)
Where speech is processedIn the cloud: audio is split into chunks and sent to a third-party speech-to-text providerOn the Mac: recognition and formatting run locally, with no cloud transcription
The recordingDeleted automatically about 30 days after upload; you can delete it soonerNot uploaded; kept on the Mac for History, then deleted on the schedule you choose
The textThe transcript is kept until you delete itStored in a local history database on the Mac
TrainingPepys does not use your content to train its own modelsAudio and text are not uploaded; an optional setting, off by default, can send a transcript to an AI provider you configure
AccountA free account is requiredNo account

Does local dictation work offline?

Often, but not by default and not for every step. Offline here means speech recognition keeps working without a connection, after any required models are on the device.

  • Models usually need a download first. Superwhisper's model page lists one-time downloads of 75 MB to 3 GB for local models, and Pepys Dictate's speech and formatting models are about 1.3 GB on first launch.
  • Licence checks differ. Pepys Dictate activates a paid licence key online once and checks it at launch when online. Other apps' pages in the table below do not describe it.
  • Cloud formatting can fail even when local transcription works. VoiceInk's cloud options and AI enhancement need a connection, while its local transcription does not.
  • Hybrid tools lose some features offline. Superwhisper says local models work offline, so a mode that uses a cloud model does not.
  1. Read the app's privacy page or security page. Look for the words "processed", "servers" and "retained", and note whether it names providers.
  2. Look for a data or privacy setting that lets you opt out of your data being used to improve models.
  3. Turn off Wi-Fi, open a text field and dictate. If text still appears, recognition ran on the Mac. If it fails, the app likely needs a connection for that step.
  4. If the policy and the offline test disagree, ask support in writing which steps run on the device.

Is local dictation faster, and is cloud dictation more accurate?

Neither is true in general. Local processing can avoid a network round trip. Cloud processing can use larger managed models and powerful remote compute, but depends on the network. Actual latency depends on the model, hardware, network and implementation.

Accuracy works the same way. Where recognition runs does not by itself decide it. Model size, training data, the domain you dictate in, your microphone, language, accent, background noise and decoding settings all matter. The published comparisons we found are written by vendors that sell one side, and they disagree on the size of any gap. This page ranks neither, and independent benchmarks are still missing.

What local and cloud dictation need from your hardware

Running a model on your own machine moves the work from a vendor's servers to your device. Cloud dictation lowers local compute needs but depends more on the network and the service being available.

  • Storage: local models are downloads, from 75 MB to 3 GB in Superwhisper's docs to about 1.3 GB for Pepys Dictate.
  • Chip and system: Pepys Dictate needs an Apple silicon Mac on macOS 13 or later. Whisper Notes needs Apple silicon and macOS 14 on the Mac. VoiceInk recommends Apple silicon and warns that local models do not work reliably on Intel Macs.
  • Memory and speed: Superwhisper's model page gives no specific RAM requirement, and recommends cloud models for older machines because they are fast on any hardware.
  • Model size is the core constraint. A review of on-device recognition research says conventional recognisers could need a language model of up to 100 GB, which made them impractical on a device, and that fully neural designs need much smaller memory footprints.

How local, cloud and hybrid dictation fail

Each architecture fails in its own ways. No probabilities are claimed here, because none have been measured.

  • Local failure modes: the model is not downloaded yet, there is not enough memory or storage, the hardware is too old for the chosen model, or the local app crashes.
  • Cloud failure modes: no internet, a service outage, high latency, service or rate limits, or an account or authentication problem. Cloud speech services publish limits: Google's Cloud Speech-to-Text lists 900 recognition requests per 60 seconds per project, and says requests beyond a limit produce an error.
  • Hybrid failure modes: a hybrid app can inherit both lists, depending on which mode you use.

Where some apps sit today

These rows come from each vendor's own pages, read on 8 October 2026. They describe architecture, not quality, and they are not ranked or priced. If local, offline or privacy is your buying criterion, see our comparison of private, local and offline dictation apps.

Where speech and text are processed, offline mode, cloud options and accounts for seven apps
ProductSpeech processingText and formattingOffline modeCloud optionAccountMain architecture
Pepys DictateLocal: speech recognition runs on your MacLocal: formatting runs on your MacYes, once its models are downloaded; a paid licence key is activated online onceNo cloud transcription. An optional advanced setting can send a transcript to an AI provider you configure; it is off by defaultNo accountLocal-first dedicated dictation
VoiceInkLocal by default: its FAQ says transcription runs locally; optional cloud transcription uses your own API keyYour choice: VoiceInk Refine runs on-device; AI enhancement sends text to the provider you select; Ollama can keep it localYes after setup: its README says processing is 100% offline; cloud options need a connectionYes, optional: cloud transcription and AI enhancement with your own API keyNot stated in public docsLocal-first dedicated dictation
MacWhisperLocal: its homepage says it transcribes locally on your Mac with local AI modelsOptional AI clean-up uses your own AI key (cloud providers) or a local model such as Ollama or LM StudioYes: its homepage lists an Offline feature for local processingYes, optional: remote models and providers with your own API keysNot stated in public docsLocal transcription suites with dictation
Whisper NotesLocal: its site says transcription runs on the device and audio never leaves itNot stated in public docsYes: its privacy page says no internet connection is requiredNone statedNo account, per its FAQLocal transcription suites with dictation
SuperwhisperYour choice per mode: local voice models or cloud modelsYour choice per mode: a local language model (S1-mini), a cloud language model, or no AI processingYes with local models: its model page says local models work offline; cloud models need a connectionYes: cloud voice and language models (Pro), or your own keysNot stated in public docsHybrid and model-selectable
Wispr FlowCloud: its data-controls page says transcription always occurs on the cloudCloud service: it uses the app name and surrounding text for formatting and punctuationNo: transcription always occurs on the cloud, per its data-controls pageYes: cloud onlySign-in is a setup step, per its setup guideCloud and cross-platform dictation
Willow VoiceCloud: its help center says Willow uses cloud-based AI modelsCloud models; optional Context Awareness reads small bits of text around the cursorPaid plans: its help center lists offline dictation under the Individual Pro plan, and its homepage says it is powered entirely by your deviceYes: cloud models by defaultSign-in required, per its help centerCloud and cross-platform dictation

A worked example: Pepys Dictate

Pepys Dictate is local-first AI dictation software for Mac. Its privacy page says speech recognition and formatting run on your Mac, with no account and no cloud transcription, and that audio is never uploaded. The speech and formatting models are about 1.3 GB and download on first launch.

Pepys Dictate goes online to download models, activate a licence key, check the licence at launch when online, and check for updates. Usage events are opt-in and contain no text or audio. An optional advanced setting can send a transcript to an AI provider you configure, and it is off by default.

Pepys Dictate does not claim that nothing ever crosses the network. It also does not control what the app you dictate into does with the text.

Which architecture fits you?

Choose by your constraints, not by a label. Each of these is a fair choice for some people.

  • Choose local if offline use matters, you prefer speech to be recognised on your own device, you work on one device, or you want less dependence on a vendor's servers.
  • Choose cloud if you need the same dictation across devices, team administration, centrally managed models, hosted history or sync, or lower local hardware needs.
  • Choose hybrid if you want a local default with optional cloud models, a different quality or speed trade-off per workflow, or the freedom to switch per mode. Superwhisper is one example.
  • For how Apple's own Dictation behaves offline, see offline dictation on Mac. For wider comparisons, see the roundup of dictation apps, the one-time purchase options or Wispr Flow as a cloud example.

Last updated November 8, 2026.

Questions

What is local dictation?

Local dictation, also called on-device dictation, runs the speech recognition model on your own device, so audio can become text without leaving it. The model is stored on the device after a download, and recognition needs no internet connection. The app can still go online for licensing, updates or optional features.

What is cloud dictation?

Cloud dictation sends your audio, and sometimes the text and context, over the internet to remote servers. The servers run the speech model and return text. It needs a connection and relies on the vendor's service, but it can offer centrally managed models, cross-device features and lower local hardware needs.

What is hybrid dictation?

Hybrid dictation lets the app or you choose local or cloud processing per mode or per step. For example, speech recognition can run locally while cleanup uses a cloud model, or each mode can pick its own models. The architecture then depends on your settings, so check each step.

Is local dictation more private?

Not automatically. Local processing reduces how much raw audio goes to a vendor's servers, but privacy also depends on telemetry, licence checks, update checks, accounts, optional AI or cloud features and the app you type into. A cloud service can also publish strong retention and training terms. Compare the data-flow statements of each app.

Does local speech-to-text work offline?

Recognition usually does, once the model is downloaded, but the whole app may not. Licence activation, cloud formatting and cloud models can still need a connection. Check each step, and test by turning off Wi-Fi and dictating.

Is cloud dictation more accurate?

Not universally. Accuracy depends on model size, training data, your domain, microphone, language, accent, noise and decoding settings more than on where the model runs. Published comparisons are mostly written by vendors, and independent benchmarks are missing. Test each app with your own voice and vocabulary.

Is local dictation faster?

Not universally. Local processing can avoid a network round trip, and cloud processing can use larger models and powerful remote compute. Actual latency depends on the model, hardware, network and implementation, so measure the apps you are considering.

Does local dictation mean no data leaves your device?

No. Local recognition can keep audio on the device, but an app may still send licence checks, update checks, analytics, optional cloud requests and account data. The app you dictate into may also send the text to its own servers. Read what the dictation app says it sends.

What is the difference between local and cloud speech recognition?

Where the model runs. Local speech recognition runs on your device and needs model downloads, storage and capable hardware. Cloud speech recognition runs on remote servers and needs a connection but little local compute. Hybrid apps use both, depending on the mode.

Which dictation apps use local processing?

According to their own pages, Pepys Dictate, VoiceInk, MacWhisper and Whisper Notes process speech on the device by default. Superwhisper lets you choose local or cloud models per mode. Wispr Flow and Willow Voice use cloud transcription by default, and Willow lists offline dictation on a paid plan. Apple Dictation is on-device for some languages.

Sources

Keep reading

Want local-first dictation on your Mac?

Free for 2,000 words a week, or $9.99 once, plus tax where applicable, for unlimited use on one Mac. Speech recognition and formatting run on your Mac.

Apple silicon, macOS 13 or later. More about Pepys Dictate