WhisperLive and whisper-speech-to-text
The first is a server-side streaming implementation of Whisper, while the second is a browser-based JavaScript client library for recording and sending audio to Whisper—making them complements designed to work together in a web architecture.
About WhisperLive
collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
Supports multiple inference backends (Faster-Whisper, TensorRT-LLM, and OpenVINO) for optimized performance across different hardware, with pluggable model sizes and a client-server architecture for concurrent transcription. Features Voice Activity Detection, real-time translation between any languages, and OpenAI-compatible REST API endpoints alongside native WebSocket streaming for low-latency audio input from microphones or files.
About whisper-speech-to-text
nitaiaharoni1/whisper-speech-to-text
Whisper Speech-to-Text is a JavaScript library for recording and transcribing user audio into text via OpenAI's Whisper, intended for web applications.
Provides real-time transcription with pause/resume control during recording sessions. Uses the Web Audio API to capture microphone input and streams audio to OpenAI's Whisper endpoint via callback-based async methods. Handles microphone permissions automatically, making it suitable for embedding directly into React, Vue, or vanilla JavaScript web applications without additional permission management.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work