TypeWhisper
DEGitHub
Back to Add-ons

WhisperKit

Bundled

by TypeWhisper

Transcription macOS
Source Code
WhisperKit settings

About

WhisperKit runs OpenAI’s Whisper models locally on your Mac using Apple’s CoreML framework. All processing happens entirely on-device with no cloud connection required. WhisperKit supports 99+ languages, English translation, and automatically selects the best model based on your available RAM.

Features

  • Fully on-device transcription via CoreML on Apple Silicon
  • 99+ languages supported
  • Translation to English
  • Voice Activity Detection (VAD)
  • Automatic model selection based on available RAM
  • No API key or cloud account needed

Transcription Models

ModelID
Whisper Tinyopenai_whisper-tiny
Whisper Baseopenai_whisper-base
Whisper Smallopenai_whisper-small
Whisper Mediumopenai_whisper-medium
Whisper Large V3openai_whisper-large-v3
Whisper Large V3 Turboopenai_whisper-large-v3_turbo
Distil Large V3distil-whisper_distil-large-v3

Configuration

No API key required. WhisperKit runs entirely on-device.

Setup

  1. Open TypeWhisper Settings > Plugins
  2. Find the WhisperKit plugin and enable it
  3. Models are downloaded automatically on first use
  4. Select WhisperKit as your transcription engine in Settings or in a profile

Manual copy workaround

If WhisperKit is already working on one Mac, you can also copy the local model files over as a workaround. This is separate from plugin installation.

  1. Quit TypeWhisper on both Macs.
  2. On the Mac where WhisperKit already works, copy only the model folders you actually use from ~/Library/Application Support/TypeWhisper/PluginData/com.typewhisper.whisperkit/models/.
  3. On the target Mac, install the same or a newer TypeWhisper version, launch it once, then quit it again.
  4. Copy those model folders into the exact same path on the target Mac: ~/Library/Application Support/TypeWhisper/PluginData/com.typewhisper.whisperkit/models/.
  5. Reopen TypeWhisper and check whether the model is detected and can be loaded.

Install from file is for plugin bundles. It does not import WhisperKit model folders for you.

This is a workaround, not the polished primary flow. If the target Mac blocks access to ~/Library/Application Support or CoreML cache usage, the copied model can still fail to load.