Voice and music · by Argmax
WhisperKit
Transcribe audio and label who spoke when, all on your Mac.
speech → text, data · speech → data · text → speech
- Way in
- Official APINo sign-up, no key
- To start
- Freeopen source (MIT); Argmax Pro SDK is paid
- Runs
- On your Mac
- Checked
- Nov 3, 2026Prices as of that day
What it can do 3
Transcribe audio on the Neural Engine with word timestampsSwift toolchain needed to build CLI/server (Xcode CLT); Homebrew route unavailable (no brew)speech → text, datafree (local)
Diarize speakersspeech → datafree (local)
Synthesize speech with Qwen-TTS on devicetext → speechfree (local)
Does the same job
Prices and limits as of Nov 3, 2026, from Argmax’s own pages. They change; check before you rely on them.Not affiliated with Argmax. Not advice.Something wrong?