Skip to main content
Local processing keeps your audio on your device. OpenWhispr supports two speech recognition engines: whisper.cpp and sherpa-onnx (NVIDIA Parakeet & Nemotron).

​
OpenAI Whisper (via whisper.cpp)

The default local engine. Choose a model based on your needs:

​
Setup

  1. Open Settings, choose Speech-to-Text under AI Models, then the tab for the mode you’re setting up — Dictation, Note Recording or Audio Upload. Each keeps its own engine choice.
  2. Choose Local, then select a Whisper model
  3. Click Download — models are stored in ~/.cache/openwhispr/whisper-models/
The whisper.cpp binary is bundled with OpenWhispr. No Python or additional runtime needed.

​
GPU acceleration

Local Whisper can run on your GPU for much faster transcription:
  • macOS — Metal acceleration is built in on Apple Silicon, no setup needed
  • NVIDIA (Windows/Linux) — one-click CUDA runtime download from the GPU card in the model picker
  • AMD / Intel (Windows/Linux) — one-click Vulkan runtime download from the same GPU card, covering Radeon and Arc/integrated GPUs
If the GPU runtime fails to start (unsupported GPU, out of VRAM), OpenWhispr automatically falls back to CPU with an in-app notice — transcription keeps working.

​
NVIDIA Parakeet & Nemotron (via sherpa-onnx)

A faster alternative to Whisper, especially on lower-end hardware.

​
Setup

  1. Open Settings, choose Speech-to-Text under AI Models, then the tab for the mode you’re setting up
  2. Choose Local, then switch the provider to NVIDIA Parakeet
  3. Download the model
Parakeet’s offline models use INT8 quantized ONNX models for efficient CPU inference. The Nemotron models are streaming models: dictation is decoded live over one persistent connection and the text is committed the moment you stop speaking — no second decoding pass — and with the live preview enabled, partial text updates as you speak. If the stream fails, transcription automatically falls back to the standard record-then-transcribe path.

​
Which to choose

  • Parakeet — best for speed, lower-end hardware, or when you need multilingual support
  • Whisper — best for quality, especially with the medium or large models

​
Disk management

Remove downloaded models anytime from Settings → System → Data Management → Model cache, using Clear cache. Open shows you the folder first. Models can be re-downloaded when needed — see where your files live.