DijiFlow Dictate turning speech into text on a Mac, fully on-device
DijiFlow Dictate floating menu-bar dictation panel with live waveform
On-device Whisper accuracy — up to 98% on clear speech
Many times faster than real time on Apple Silicon
DijiFlow Dictate dictation panel with a live waveform on a Mac
On-device privacy: your audio stays on your Mac, never the cloud
DijiFlow Dictate turning speech into text on a Mac, fully on-device DijiFlow Dictate floating menu-bar dictation panel with live waveform On-device Whisper accuracy — up to 98% on clear speech Many times faster than real time on Apple Silicon DijiFlow Dictate dictation panel with a live waveform on a Mac On-device privacy: your audio stays on your Mac, never the cloud

DijiFlow Dictate — Pro

About this app

DijiFlow Dictate — Pro turns your voice into text anywhere on your computer. Press a hotkey, speak, and the words land at your cursor in any app. Everything runs 100% on-device with WhisperKit and CoreML — no account, no cloud, no telemetry. Pro unlocks unlimited file length, the largest, most accurate models, speaker labels, timestamps and custom vocabulary. Pick the term that fits below.

Free 30-day Pro trial · 30-day refund · 100% on-device · No account · On Mac and Windows.

Model & performance

Built on Whisper, running fully on your device.

Pro uses OpenAI's largest Whisper speech models on-device with WhisperKit and CoreML — Apple Neural Engine and GPU. Nothing is uploaded, ever.

macOS 14 (Sonoma)+Apple Silicon (M1 or newer)Mic + Accessibility permissionWindows 10/11 (AMD · Intel · NVIDIA)
Built on Whisper,
98%accuracy on clear speech (largest model)
15×faster than real time, on-device
29languages, fully offline
No servers100% on your device
300 MB–6 GBspeech model — base to Large-v3 (downloaded once)
~5 MBapp size — models download on demand
What Pro unlocks

One small app, every dictation feature.

Push-to-talk, files, speaker labels, 29 offline languages and custom vocabulary — all running 100% on your computer.

Push-to-talk & toggle

Hold a hotkey to dictate, or toggle hands-free — text lands at your cursor.

Unlimited file & video

Drop in audio or video of any length and get a clean, searchable transcript.

Speaker labels + timestamps

Diarization and timecodes for meetings and interviews.

29 languages, offline

Transcribe in 29 languages with no internet after the first model download.

Vocabulary packs

Teach DijiFlow your names, jargon and acronyms for sharper accuracy.

100% on-device

Audio never leaves your computer — no account, no servers, no telemetry.

How it works

Three steps, zero friction.

Press a hotkey, speak, and your words land as text wherever your cursor is — in any app, fully on-device.

1

Press the hotkey

Press your hotkey from anywhere on your computer.

2

Speak naturally

Talk the way you think — in any app, in any of 29 languages.

3

Your text appears

Pasted at your cursor, instantly — nothing ever leaves the device.

Choose your term

Pick a plan, check out instantly.

One app, pick your term. Free is free forever; every Pro plan unlocks the same full feature set — they differ only by how long the licence lasts.

Free

£0 forever

No account, no card. Yours to keep.

Download for MacmacOS 14+ · Apple Silicon Download for WindowsWindows 10 / 11
Hotkey slots1 slot3 slots
File length3 minUnlimited
File & video transcription—
Speaker labels & timestamps—
Vocabulary packs—
GPU / Neural Engine + largest models—
All 29 languages
Private by design

Your words never leave your machine.

Every recording is transcribed locally on your computer. No upload, no copy on a server, no exception.

  • No telemetry — we collect nothing
  • No account or sign-in required
  • No cloud transcript, ever
  • Works fully offline after setup
Why on-deviceFor business