For Mac & Windows

Download DijiFlow Dictate, free.

Private, on-device voice-to-text for your computer. No account, no card, no waiting.

Free forever · No account · 100% on-device

Unlimited dictation. No credits, no caps.

Unlimited dictation with your subscription · Talk or transcribe files as much as you want · No credits, no usage caps · Free forever plan · Lifetime licence available

Get the app

Choose your platform

Lightweight app. Speech models download on first use; after that, fully offline.

No credits · No limits

Download for Mac

v7.17

macOS 14 Sonoma+ · Apple Silicon

  • Unlimited on-device dictation
  • All 90+ languages, offline
  • No account, no card, no telemetry
  • Upgrade to Pro anytime in-app

Windows

Windows 10 / 11v7.16

Native build for Windows 10 & 11 — runs on AMD, Intel and NVIDIA GPUs. NVIDIA needs the latest GPU driver + CUDA runtime; AMD & Intel just need up-to-date drivers.

  • Unlimited on-device dictation
  • All 90+ languages, offline
  • No account, no card, no telemetry
  • Upgrade to Pro anytime in-app
Download for WindowsWindows 10 / 11
macOS 14+ · Apple Silicon Windows 10 / 11 · AMD · Intel · NVIDIA NVIDIA: latest driver + CUDA Mic + Accessibility 300 MB–6 GB model, downloaded once
System requirements

What you need to run it.

A small menu-bar app that runs entirely on your computer. No internet needed after the first model download. Pick your platform.

macOS 14 (Sonoma) or newerApple Silicon (M1 or newer)Microphone + Accessibility permission

Everything runs on your Mac. No internet needed after the first model download.

macOS 14+
Sonoma or newer
Apple Silicon
M1+ — Neural Engine & GPU
Free
forever — no account or card
300 MB–6 GB
speech model, base to Large-v3
No servers
100% on your device, offline
29
languages, on-device
Windows 10 or 11 (64-bit)AMD, Intel or NVIDIA GPUNVIDIA GPUs: install CUDAAMD / Intel GPUs: latest driversMicrophone permission

NVIDIA users install CUDA; AMD and Intel users keep GPU drivers up to date.

Windows 10/11
64-bit
GPU accelerated
AMD · Intel · NVIDIA
Free
forever — no account or card
300 MB–6 GB
speech model, base to Large-v3
No servers
100% on your device, offline
29
languages, on-device
Free and Trial need no purchase

Ready for more? Go Pro.

Unlimited files, speaker labels, vocab packs and the largest models — start a free 30-day trial in-app.

Unlimited dictation. No credits, no caps.