How to use from the
Use from the
WhisperKit library
# Install CLI with Homebrew on macOS device
brew install whisperkit-cli

# View all available inference options
whisperkit-cli transcribe --help

# Download and run inference using whisper base model
whisperkit-cli transcribe --audio-path /path/to/audio.mp3

# Or use your preferred model variant
whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose

SpeakerKit Core ML

Read the blog

Try it on Argmax Playground (TestFlight)

Read the Interspeech 2025 paper for architecture and benchmarks.

License: SpeakerKit the Swift framework has MIT license. The models SpeakerKit is built on have CC BY 4 license.

Downloads last month
41,563
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support