JSPM

Node.js bindings for OpenAI's Whisper. Runs local on CPU.

AugnitoSDK lets you make use of the Speech Recognition AI. You can edit, format and complete reports at the speed of human speech, with the best-in-class accuracy

BFL - Blind friendly library

JavaScript modules for Mozilla's cloud speech recognition API

https://haji-api.ir وب سرویس های حاجی

A binding for OpenAI's Whisper Speech-to-Text system, supporting async operations.

A simple and lightweight proxy for seamless integration with multiple STT (Speech-to-Text) providers including Whisper.cpp

Local audio transcription on CPU. Node.js bindings for OpenAI's Whisper.

npm package for calculating the character-error-rate between two strings to evaluate speech recognition quality

Node bindings for OpenAI's Whisper. Optimized for CPU.

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

Chinese speech to text with Baidu service

A library for text-to-speech (TTS) and speech-to-text (STT) operations using Google Cloud and OpenAI.

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

Open source cross platform decentralized always-on speech recognition framework

Plugins for the LipSurf Chrome extension. Each plugin adds a set of commands to LipSurf.

Local audio transcription on CPU. Node.js bindings for OpenAI's Whisper.

Audio file transcription services. Your speech. Private.

Node bindings for OpenAI's Whisper. Optimized for CPU. (Updated with latest whisper.cpp September 2023)

A JavaScript library enabling in-browser audio recording and transcription using OpenAI's Whisper Speech-to-Text

A module to stream audio to a speech recognition server and get back the STT result"

AugnitoSDK lets you make use of the Speech Recognition AI. You can edit, format and complete reports at the speed of human speech, with the best-in-class accuracy

Wrapper around LinTO Studio API

Coqui STT runtime transcript NodeJs client, including server usage examples.

AI model wrapper using x402 payment for pay per request

A wrapper for Azure Speech Services Speech to Text REST API

A lightweight npm utility built on the Google speech-to-text API for converting pre-recorded speech to text, ideal for processing audio files, creating captions, and enhancing accessibility.

OpenClaw 语音输入插件 - 通过浏览器麦克风进行语音识别后，与 OpenClaw 对话

Local audio transcription on CPU. Node.js bindings for OpenAI's Whisper. Modified from node-whisper

Module for using Mozilla's speech-to-text API from Node.js

A reveal.js plugin that adds real-time, auto-scrolling subtitles to your presentation.

```shell npm i use-speech-vue3 ``` ```shell yarn add use-speech-vue3 ``` ```shell pnpm i use-speech-vue3 ```

AugnitoSDK lets you make use of the Speech Recognition AI. You can edit, format and complete reports at the speed of human speech, with the best-in-class accuracy

convert __dirname from CommonJS into ESModule System