WhisperKit setup — Swift, CLI, CoreML models & fixes

Run Argmax's WhisperKit on Apple Silicon: Swift package setup, the whisperkit-cli, CoreML model downloads, and fixes for compile-time and first-run stalls.

Setup that works

1

CLI

brew install whisperkit-cli then whisperkit-cli transcribe --audio-path file.m4a. First run downloads + specializes a CoreML model.

2

Swift package

Add https://github.com/argmaxinc/WhisperKit in Xcode; iOS 16+/macOS 13+ targets.

3

Models

Models pull from the Hugging Face argmaxinc repo automatically; --model large-v3 selects size.

Skip the setup — paste the file here

Same Whisper-class accuracy, no install, no model downloads, no GPU questions. Speaker labels, word timestamps and every export (TXT, SRT, VTT, DOCX) included. Free instant preview; credits from $2 and they never expire.

Fixing the common errors

First run hangs for minutes

CoreML “model specialization” compiles the model for your exact chip on first load — up to several minutes for large-v3. It's cached afterward; don't kill it.

Works on my M2, crawls on Intel

WhisperKit targets the Apple Neural Engine — Intel Macs aren't the audience. Use whisper.cpp or a hosted engine there.

No speaker diarization?

Correct — WhisperKit transcribes only. Pair it with a diarization service, or use a hosted pipeline that returns labeled speakers.

App Store build rejected for model size

Ship the tiny/base model in-app and download larger models on first launch — Apple's cellular download cap applies to the bundle, not post-install downloads.

More on WhisperKit: the full WhisperKit page · WhisperKit alternatives · all transcription tools