Version
1.0.3
Operating system
Windows 10 1809+ or Windows 11
Architecture
64-bit
Download size
238 MB
Before you install

Pick the model that fits this PC.

Koeva now lets you choose the local transcription model during installation. Start light on modest machines, or choose a larger model when accuracy matters more than resource usage.

  • Windows 10 version 1809 or later, or Windows 11, 64-bit
  • A recent CPU; Vulkan-compatible graphics are optional and accelerate transcription
  • Enough free SSD space for Koeva, shared components, and the selected transcription model
  • A lighter model for modest hardware, or a larger model for higher accuracy on stronger machines
Model selector

Choose a model, then check the hardware.

Transcription model

Recommended default for strong consumer PCs.

Accuracy
Very good
Speed
Fast
Model file
834 MB
Memory
16 GB RAM
Processor
Recent 4-core / 8-thread CPU or better
Graphics
Optional; dedicated NVIDIA, AMD, or Intel Vulkan GPU with 6 GB+ VRAM recommended. CPU fallback is slower.
Storage
Keep 5 GB free for Koeva, shared components, and working space.
  • This is Koeva's default balance of speed and quality.
  • Choose it first when the computer has a current dedicated GPU and enough graphics memory.
View model requirements
After download

Install in three steps.

  1. 01

    Download the official Koeva installer.

  2. 02

    Open the installer and follow the Windows prompts.

  3. 03

    Choose the first transcription model from the installer list.

  4. 04

    Launch Koeva and let the selected local speech model finish loading.

Need help before installing?