vosk-browser and vosk-server
These are complements: the browser library handles client-side speech recognition in WebAssembly, while the server provides alternative remote recognition via WebSocket/gRPC/WebRTC for applications that need server-based processing instead of or alongside in-browser inference.
About vosk-browser
ccoreilly/vosk-browser
A speech recognition library running in the browser thanks to a WebAssembly build of Vosk
Explicitly targets WebWorker execution to avoid blocking the main thread, with support for real-time microphone input or pre-recorded audio files across 13 languages. Integrates with the Web Audio API for audio processing and provides both npm and CDN distribution, offering event-based result callbacks for partial and final recognition outputs. The library wraps an updated Vosk WebAssembly build with a JavaScript API, handling model loading and audio pipeline management.
About vosk-server
alphacep/vosk-server
WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
Provides four distinct server implementations supporting MQTT, gRPC, WebRTC, and WebSocket protocols for flexible deployment scenarios. Built on Vosk-API and Kaldi for entirely offline speech recognition without cloud dependencies. Designed for integration with smart home systems, PBX platforms like Freeswitch and Asterisk, web applications, and chatbot backends requiring real-time streaming transcription.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work