WhisperKit
Argmax's open-source Swift framework for running OpenAI Whisper speech-to-text on Apple devices, now shipped in the Argmax Open-Source SDK alongside SpeakerKit and TTSKit.
About WhisperKit
Apps that send audio to a cloud transcription API add latency, per-minute costs and privacy concerns.
Who it’s for
- iOS and macOS developers adding offline transcription to their apps
- Teams that want speech-to-text without sending audio to a server
When to consider it
Consider WhisperKit when you want Whisper transcription running on-device in a Swift app, with a command-line tool and a local server for testing.
Tradeoffs & limitations
- MIT licensed; building with the Swift package requires macOS 14 or later and Xcode 16 or later.
- Real-time transcription with speakers, custom vocabulary and Android support are in the paid Argmax Pro SDK, priced at $1.33 per device per month on monthly billing with a 1,000-licence monthly minimum.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use WhisperKit.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 31, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Argmax Open-Source SDK (WhisperKit) on GitHub
Argmax's open-source Swift framework for running OpenAI Whisper speech-to-text on Apple devices, now shipped in the Argmax Open-Source SDK alongside SpeakerKit and TTSKit.
Based on official pages and announcements checked on 2026-10-31. No hands-on test, performance benchmark or popularity ranking is claimed.