Browser-native audio transcription powered by WebGPU Whisper — zero server, fully local.
Work with the output of the OpenAI Whisper API
Helpers for using Whisper.cpp in browser using WASM
Helpers for installing and using Whisper.cpp
Node bindings for OpenAI's Whisper. Optimized for CPU.
Run Whisper on Node.js
Run Whisper on Node.js
Node.js bindings for OpenAI's Whisper. Runs local on CPU.
Speech-to-text recognition API for Tauri with multi-language support
TypeScript port of SYSTRAN/faster-whisper for Node.js, built on CTranslate2, Koffi, FFmpeg, and ONNX Runtime.
Run Whisper on Node.js
Talking Head (3D): A JavaScript class for real-time lip-sync using Ready Player Me full-body 3D avatars.
Whisper.cpp Node.js binding with auto model offloading strategy.
An easy-to-use speech toolset. Includes tools for synthesis, recognition, alignment, speech translation, language detection, source separation and more.
A task-based automation app. Leiningen style.
A GPU accelerated .node addon for whisper.cpp with prebuilt binaries
A library for obtaining browser versions with their maximum supported Baseline feature set and Widely Available status.
React Hook for OpenAI Whisper API with speech recorder and silence removal built-in.
transcription addon for qvac
Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.
Web3 module to interact with the Whisper messaging protocol.
A CLI and Node.js library to help retrieve, display, and store Google search results
Pi extension. Voice dictation via /voice — local on-device STT with sherpa-onnx Whisper (base multilingual int8), microphone capture via decibri.
Linux-first desktop AI assistant built with Tauri, React, and TypeScript.