← Blog

Offline Dictation with Parakeet

Your voice, your device, your text. Once you have downloaded it and it is loaded, Hovor's optional Parakeet model transcribes speech entirely on your supported Mac or iPhone and the audio is not uploaded. If the model is still loading — after an app relaunch, or while it is still downloading — that recording falls back to server transcription.

Last updated: October 6, 2026

What "on-device" actually means

"On-device" means Hovor's Parakeet speech model runs the entire transcription step directly on your Mac or iPhone's own chip — audio is captured, converted to text, and discarded locally, with no network call carrying it anywhere. One caveat matters: this holds once the model is loaded. If the model is still loading — after an app relaunch, or while it is still downloading — that recording falls back to server transcription. This differs from cloud dictation, where audio always uploads to Hovor's server, and OpenAI or Hovor's own self-hosted speech model transcribes it, before a transcript returns.

On-device Parakeet covers the speech-to-text step only. Turning that raw transcript into cleaned-up, styled text (grammar, punctuation, tone) is a separate stage that still needs Hovor's server, Apple's on-device models on iPhones with Apple Intelligence (iOS 26+), or your own BYOK key — Hovor's fully local tone-formatting code exists but is not functional on any platform today.

Cloud dictationOn-device Parakeet
Where audio goesUploaded to Hovor's server, transcribed by OpenAI or Hovor's own speech modelOn-device when the model is loaded; server fallback while it is loading
Works without networkNoYes, after a one-time model download
Latency sourceNetwork round trip + server queue + API inferenceOn-device inference only (CPU on iOS; CPU + Neural Engine on macOS)
Cost modelCounts against the 2,000 words/week free pool; Pro has no weekly word limitCounts against the same free pool; one-time Local Unlock removes the cap
Device requirementNo RAM or storage gateSupported Macs: no RAM gate. iOS: ≈4 GB+ RAM, plus a server-side flag must be on

Why offline = private

Offline dictation is private because there is no server in the loop to breach, subpoena, or leak: audio processed on-device by Parakeet does not cross a network boundary, so there is nothing for a company, attacker, or legal request to intercept. This applies to recordings made once the model is loaded; a recording taken while the model is still loading falls back to server transcription. Cloud dictation instead sends audio to remote infrastructure, where confidentiality depends on encryption and written policy rather than on the audio simply never leaving your hands.

If you are dictating:

…the question "who can hear this?" has a simple answer: only you, once the model is loaded — the audio is not uploaded to Hovor's server or any other server. The one exception is the model-loading window itself, when that recording falls back to the server.

For users subject to professional confidentiality obligations (lawyers, doctors, therapists, journalists), on-device dictation is not just a preference. It is often the only architecture that satisfies their obligations.

Works without internet

Offline dictation keeps working with zero network connectivity because the Parakeet model, once downloaded, runs entirely on your device's CPU (iOS) or CPU and Neural Engine (macOS) — there is no round trip to fail. Cloud dictation, by contrast, stops the moment your connection drops, because its transcription step depends on reaching Hovor's server.

On a long-haul flight. On a train through a tunnel. In a basement office with poor signal. In a country with unpredictable mobile coverage. In a meeting room where IT policy blocks outbound traffic. Wherever cloud dictation fails or becomes unreliable, on-device Parakeet keeps transcribing at the same quality.

Once the model is loaded, there is no spinner and no "waiting for server" delay — it runs whether or not a router is nearby. The one window where a router still matters is right after an app relaunch or while the model is still downloading, when a recording falls back to server transcription.

Parakeet: the model Hovor runs locally

Hovor runs Parakeet TDT 0.6B v3, a speech-recognition model NVIDIA built and released under the CC-BY-4.0 licence (verified against NVIDIA's published model card, checked 2026-07-19); Hovor did not train it. The model supports 25 European languages, including Ukrainian, trained with balanced sampling across languages and a single 8,192-token tokenizer shared across all of them — no per-language switching required.

Ukrainian gets the same training weight as German or French.

On iOS, Parakeet runs CPU-only rather than using the Neural Engine — a deliberate trade-off tied to background-execution limits on iOS for processes like the keyboard extension. On macOS it runs with both CPU and Neural Engine, which keeps it fast and battery-efficient.

Hovor selects and ships Parakeet; it does not fine-tune or modify it. The quality reflects NVIDIA's engineering on the model, and Hovor's engineering on the pipeline around it.

Turning on offline dictation (and Local Unlock)

On-device Parakeet is optional: you download the model first, and it is cloud dictation until then. It is available on supported Macs, and on iPhones with roughly 4 GB of RAM or more — a server-side flag can also disable it independently of your hardware. Free plans can use it within the weekly pool; Local Unlock, a one-time $20.00 / 880 UAH purchase, sold through the App Store on iOS and macOS (family-shareable there), and separately via Monobank on the web, removes that cap — no subscription.

PlatformOn-device ParakeetRequirement / status
macOSYesAvailable on supported Macs, no RAM gate
iOSYes, conditional≈4 GB+ RAM device, and the server-side parakeet_enabled flag must be on
WindowsYes, opt-in (beta)Download the model in Settings; the Windows beta needs a CPU with AVX2 support

The free plan's 2,000 words per week are one pool shared by cloud and on-device dictation; Local Unlock lifts the cap for on-device dictation. Local Unlock also includes unlimited dictionary replacements, snippets, and custom workflows; it is a single purchase that covers all the features that run entirely on your device.

To switch to on-device mode:

  1. Open Hovor on your Mac or iPhone.
  2. Go to Settings → Dictation → Speech model.
  3. Select Parakeet (on-device).
  4. Hovor will download the model if it is not already on your device. This is a one-time download over Wi-Fi; after that, no connection is needed.

Good to know: model download and device requirements

Parakeet downloads once over Wi-Fi and then needs no connection for transcription, including model updates you trigger manually from Settings; the download requires a modest amount of local storage, shown before you start. On-device Parakeet covers speech-to-text only — text formatting still needs the server, Apple's on-device models (iPhones with Apple Intelligence, iOS 26+), or your own BYOK key, since Hovor's fully local tone-formatting path is not shipped.

Frequently asked questions

Does offline Parakeet dictation also format and clean up my text without internet?

No, not fully. On-device Parakeet handles only the speech-to-text step: once the model is loaded, your voice becomes a raw transcript entirely on your device, with no network call. If the model is still loading — after an app relaunch, or while it is still downloading — that recording falls back to server transcription. Turning that raw transcript into formatted, toned final text (grammar, punctuation style, casual vs. formal) is a separate stage that still needs either Hovor's server, Apple Foundation Models on iPhones with Apple Intelligence (iOS 26+; also on-device, but a distinct feature from Parakeet), or your own BYOK key. Real tone formatting always runs through one of the three paths above. If you dictate with no network at all and don't have Apple Foundation Models enabled, you get the raw Parakeet transcript without automatic formatting.

What happens to my audio when I use on-device Parakeet transcription?

When the on-device model is loaded, transcription runs entirely on your device and the audio is not uploaded. If the model is still loading — after an app relaunch, or while it is still downloading — that recording falls back to server transcription. With the model loaded there is no network call carrying your voice, so there is no server log to audit and no third-party infrastructure in the path. Hovor's cloud dictation, by contrast, always sends audio to Hovor's server, where OpenAI or Hovor's own self-hosted speech model produces the transcript.

Which Hovor platforms support on-device Parakeet dictation?

macOS, iOS, and the Windows beta (opt-in). On supported Macs, Parakeet is available with no RAM gate. On iOS, it requires roughly 4 GB of device RAM or more, and it can also be switched off server-side independently of your hardware via a feature flag. The Windows beta itself needs a CPU with AVX2 support; on it, on-device Parakeet is optional: download the model in Settings, and until then dictation uses Hovor's cloud.

How much RAM does my iPhone need for offline dictation?

Roughly 4 GB of physical memory or more. Hovor checks your iPhone's memory against a 4,000,000,000-byte threshold before showing the on-device Parakeet option in Settings; iPhones with less RAM won't see it at all. On top of the RAM gate, a server-side flag can also disable Parakeet independently of your device's hardware. macOS has no RAM gate on supported Macs.

Does Local Unlock require a subscription?

No. Local Unlock is a one-time, non-consumable purchase — $20.00 or 880 UAH — sold through the App Store on iOS and macOS, and separately via Monobank on the web. App Store purchases are family-shareable, it never expires, and it covers on-device Parakeet dictation plus unlimited dictionary replacements, snippets, and custom workflows, all in a single purchase. Hovor's free tier (2,000 words per week, shared between cloud and on-device dictation) and Pro subscription remain separate, unaffected by whether you've bought Local Unlock.

Which languages does Parakeet support, and is Ukrainian among them?

Parakeet TDT 0.6B v3 supports Ukrainian and other European languages, using a single tokenizer and balanced training sampling across all of them, per NVIDIA's published model card. Ukrainian gets the same training weight as German or French.

Dictate privately, without the internet

Download Hovor for Mac or iPhone. Free tier includes 2,000 words/week, shared between cloud and on-device dictation. Local Unlock adds unlimited on-device Parakeet: one-time purchase, family-shareable on the App Store, no subscription.

Get Hovor