WhisperKit and whisper-web

These are **complements** — WhisperKit provides an optimized inference engine for Apple Silicon devices, while whisper-web enables browser-based transcription, allowing developers to choose the platform (native iOS/macOS vs. web) best suited for their deployment needs.

WhisperKit
58
Established
whisper-web
47
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 19/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 5,775
Forks: 516
Downloads:
Commits (30d): 3
Language: Swift
License: MIT
Stars: 3,257
Forks: 421
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About WhisperKit

argmaxinc/WhisperKit

On-device Speech Recognition for Apple Silicon

This tool helps Apple users convert spoken audio into written text directly on their devices, without needing an internet connection. You provide an audio file, and it quickly generates a transcription with features like word timestamps and speaker identification. It's designed for developers building apps for macOS, iOS, or iPadOS that require robust, private speech-to-text capabilities.

app-development audio-transcription voice-user-interface on-device-AI speech-recognition

About whisper-web

xenova/whisper-web

ML-powered speech recognition directly in your browser

This tool helps you convert spoken audio into written text, all within your web browser without sending data to a server. You feed it an audio recording (like a voice note, meeting recording, or spoken lecture), and it produces a precise transcription. It's ideal for anyone who needs to quickly get text from speech, such as journalists, researchers, or students.

audio-transcription voice-to-text meeting-minutes research-interviews lecture-notes

Scores updated daily from GitHub, PyPI, and npm data. How scores work