Overview

• STILL UNDER DEVELOPMENT!
• A speech recognizer built on Vosk that can be run on the browser, inspired by vosk-browser, but built from scratch and no code taken!
• Designed with strong exception safety
• See the usage folder's README.md for API documentation, notes.
• See the devel folder for the newest build (not guaranteed to work) and the JS build script

Additions to vosk-browser:

• Download multiple models
• Model storage path management (for multiple models)
• Model ID management (for model updates)
• Massively smaller JS size (>5.7MB vs 1.7MB)
• All related files (worker.js, worklet processors,...) are bundled
• Shorter from-scratch build time

Basic usage

• Use the prebuilt binary through JsDelivr.