Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.openwhispr.com/llms.txt

Use this file to discover all available pages before exploring further.

Local processing keeps your audio on your device. OpenWhispr supports two speech recognition engines.

​
OpenAI Whisper (via whisper.cpp)

The default local engine. Choose a model based on your needs:
ModelSizeSpeedQuality
tiny~75 MBFastestBasic
base~142 MBFastGood (recommended)
small~466 MBModerateBetter
medium~1.5 GBSlowHigh
large~3 GBSlowestBest
turbo~1.6 GBFastGood

​
Setup

  1. Go to Settings > Speech Recognition > Local
  2. 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.

​
NVIDIA Parakeet (via sherpa-onnx)

A faster alternative to Whisper, especially on lower-end hardware.
ModelSizeLanguages
parakeet-tdt-0.6b-v3~680 MB25 languages
parakeet-unified-en-0.6b~631 MBEnglish (state-of-the-art accuracy)

​
Setup

  1. Go to Settings > Speech Recognition > Local
  2. Switch the provider to NVIDIA Parakeet
  3. Download the model
Parakeet uses INT8 quantized ONNX models for efficient CPU inference.

​
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 > General > Local Model Storage > Remove Downloaded Models. Models can be re-downloaded when needed.