WhisperARCon Windows.

Run Whisper locally on Windows for free or switch to paid Cloud for online transcription.

Download for WindowsRead installation guide
Version
1.11
Operating system
Windows 10 1809+ or Windows 11
Architecture
64-bit
Released
October 22, 2026
Download size
184 MB
Included with WhisperARC

Local first. Cloud when needed.

  • Unlimited Local ModeAll local features are free.
  • Up to 150 Cloud hoursMonthly transcription equivalent; translation and Assistant share the same budget.
  • 14 translation languagesFor microphone dictation only. Files and system audio stay in their source language.
  • Reliable long jobsResume after restart and notify when done.
Before you install

Choose a local Whisper model.

Choose a local Whisper transcription model during installation. Large v3 Turbo q5 is preselected for a balance of quality, speed and storage. Pick a lighter model for modest hardware or a larger one when recognition quality matters more than resource use.

  • Windows 10 version 1809 or later (64-bit) or Windows 11 (64-bit)
  • A recent CPU; Vulkan-compatible graphics are optional and accelerate Local Mode
  • Enough free SSD space for WhisperARC, shared components and the selected transcription model
  • A lighter model for modest hardware or a larger model when recognition quality matters more than resource use
  • Internet for installation, models, updates, licenses and Cloud; Local transcription works offline afterward
Model selector

Choose a model then check the hardware.

Transcription model

Installer default for balanced quality, speed and storage.

Accuracy
Very good
Speed
Very fast
Model file
547 MB
Memory
16 GB RAM
Processor
Recent 4-core / 8-thread CPU or better
Graphics
Optional. A dedicated Vulkan GPU with 4 GB+ VRAM is recommended. CPU fallback is slower.
Storage
Keep 4 GB free for WhisperARC, shared components and working space.
  • This is the model currently preselected by the WhisperARC installer.
  • Whisper large-v3-turbo keeps the large-v3 family but reduces decoder layers from 32 to 4. This improves speed with a small quality tradeoff.
  • Q5 quantization reduces disk and memory pressure compared with heavier variants.
View model requirements
After download

Install in five steps.

  1. 01

    Download the official WhisperARC installer.

  2. 02

    Run it and choose English, French, German, Italian or Spanish.

  3. 03

    Choose a first transcription model. Large v3 Turbo q5 is preselected.

  4. 04

    Finish the installation while WhisperARC downloads the selected model.

  5. 05

    Open WhisperARC and let the model finish loading.

Need help before installing?