JSPM

Artyom is a Robust Wrapper of the Google Chrome SpeechSynthesis and SpeechRecognition that allows you to create a virtual assistent

Enhanced MCP Server for interactive communication between LLMs and users with custom sound notifications, approval workflows, clipboard support, and improved user experience.

An Open-source Voice & Video Calling UI Component Based on Tencent Cloud Service.

See our [React Quickstart](https://docs.vocode.dev/react-quickstart) for set up!

npm wrapper for responsivevoice.js obtained from dataplusscience.com

React components and hooks for live speaker detection and mic analysis.

A powerful React hook for real-time voice streaming, designed for AI-powered applications. Perfect for real-time transcription, voice assistants, and audio processing with features like silence detection and configurable audio processing.

🖐️🎤 Micdrop: Real-Time Voice Conversations with AI

Capacitor plugin for voice recording

Cobra VAD engine for web browsers (via WebAssembly)

A speech to text module for the discord voice implementation

Web Interface for reading and testing notifications during development

Create a new Twilio agent with a single command

Custom React hook for audio visualization from voice input or audio files

Cheetah Speech-to-Text engine for web browsers (via WebAssembly)

A custom filter library for speech enhancement

OpenAI implementation for @micdrop/server

React hook for Cheetah Web SDK

The Inworld Runtime SDK is the first AI runtime built for consumer applications. Ship faster, automate operations, and experiment in real-time.

A high-performance React Native library for text-to-speech on iOS and Android

React Native Native Voice library for iOS and Android

The Voxa CLI tools

🖐️🎤 Micdrop: Real-Time Voice Conversations with AI

AfricasTalking voice client SDK

React Native Native Voice library for iOS and Android, folk from @react-native-voice/voice

Mistral implementation for @micdrop/server

Experiment for making video streaming work for discord selfbots

Infobip Node Client

Alan Web SDK: a lightweight JavaScript library for adding a voice experience to your website or web application

Universal text-to-speech library using Microsoft Edge's online TTS service. Works in Node.js and browsers WITHOUT needing Microsoft Edge, Windows, or an API key

Transforms the text in speech and hear it using Sonos player or generate an audio file to be used with third parties nodes. Works with voices from Amazon, Google (without credentials as well), Microsoft TTS Azure, ElevenLabs.io TTS or your own voice. You

This SDK enhances the functionality of the Telesign Self-service Node SDK, providing access to a broader range of Telesign APIs. See our source code on GitHub (https://github.com/TeleSign/node_telesign_enterprise) for installation instructions and other d

N8N Community Node for Groq Text-to-Speech API integration

A lightweight token generator for 4Players ODIN

Real-time audio noise reduction with advanced chunked processing for web applications

Rhino Speech-to-Intent engine for web browsers (via WebAssembly)

Koala Noise Suppression engine for web browsers (via WebAssembly)

This package creates Speech Synthesis Markup Language (SSML) using the builder pattern.

A React hook that converts speech from the microphone to text and makes it available to your React components

Embeddable AI chat widget with voice support

Hamsa AI - Voice Agents JavaScript SDK

Get audio PCM stream data for React Native

Official Node.js SDK for Betatel telecommunications services - SMS, Voice, Calls, and more

Lightweight React Audio hooks library for Recording and Playing Audio based on MediaStream Recording API

n8n community node for ivrapi API integration

Unlimited AI models and Canvas library. Supports ts & js (supports front/back end).

Voice plugin for the Cypress Test Runner

React component for Rhino Web SDK

React Native Text-To-Speech module for Android and iOS

MCP Server for VoiceCommit widget management and feedback operations

Millis AI's web sdk to build voice agents on web and browser extension.

Advanced React speech-to-text library with real-time audio analysis and comprehensive speech metrics

Real time audio stream for react native

Official SDK for SLNG.AI Voice API - Text-to-Speech, Speech-to-Text, and LLM services

MCP server for AI assistant with ElevenLabs text-to-speech integration

NodeJS library to make stream any audio on discord easier.

ElevenLabs implementation for @micdrop/server

A React-Native Bridge for the Google Dialogflow SDK

Ultra-small native module to play streaming 16-bit PCM (mono) in React Native (Android + iOS).

A React WebRTC voice chat widget component

Orca Text-to-Speech engine for web browsers (via WebAssembly)

PIOPIY WebRTC javascript browser SDK

AI SDK implementation for @micdrop/server

Cosmicord.js is a powerful and intuitive Lavalink wrapper designed to simplify the process of integrating Lavalink into your Node.js applications.

Charisma.ai SDK for Javascript (browser)

A mobile-friendly audio player for React with a modern look and convenient usage.

Nodejs SDK wrapper for Termii API written with Typescript support

Simple one-to-one WebRTC video/voice and data channels, which drops stream support from simple-peer to improve performance and reduce bundle size

A powerful real-time communication SDK for voice interactions with Coze AI bots | 扣子官方实时通信 SDK，用于与 Coze AI bots 进行语音交互

AudioPod SDK for Node.js and React - Professional Audio Processing powered by AI

A JavaScript library for easy and efficient voice recording tasks.

Picovoice Leopard Node.js binding

Backend audio file to text transcription using Web Speech API with Puppeteer

VibeSync is a simple library for managing custom statuses in Discord Voice Channels. Easily set and update your channel statuses to keep your server engaging and organized.

Real-time voice interaction for Claude Code. Speak naturally while Claude works - interrupt, redirect, or provide continuous feedback without stopping.

Lightweight WebRTC browser library that supports video, audio and data channels

Jitsi Meet SDK wrapper for React Native.

Core library for AITuber OnAir providing voice synthesis and chat processing

Voice AI for developers - Vapi CLI

The WebSocket/WebRTC library by lirax.ua (PBX Cloud Platform)

React client for the PrimVoices Agents API

A Framework for creating Amazon Echo (Alexa) skills using Node.js

Type definitions and helpers for a Discord music player (MusicPlayer) without external dependencies

An SDK for sendchamp.com

Voice recorder component for react

Check for valid SSML

Picovoice Orca Node.js binding

Embeddable voice chat widget for Logikron Talk - enables real-time voice conversations with AI agents on any website

A flexible GUI for interacting with Speech Recognition

Get live audio recorder data for React Native

Node-Red nodes for google-home-notify library. With this node you can cast any String (up to 200 chars) to any google cast device.

Qiscus Meet SDK wrapper for React Native.

PIOPIY REST API client for nodejs,It support Voice,SMS,WhatsApp and MLAudio.

Embeddable voice feedback widget for VoiceCommit enterprise customers

Integrates the Twilio Voice SDK into Capacitor

🎙️ Real-time conversational audio with AI transcription. Build ChatGPT-style voice interfaces in minutes with <300ms latency

React Native Text-To-Speech module for Android and iOS

Production-ready speech detection using Silero VAD ONNX model for web browsers

Eagle Speaker Recognition engine for web browsers (via WebAssembly)

Text-to-Speech API wrapper for ttsmp3.com

Core library to check for valid SSML

Higher-level (L2) constructs for AWS LexV2 bot creation using the AWS CDK

Gladia implementation for @micdrop/server

React Hook for OpenAI Whisper API with speech recorder.

Mic input activity detection

Play audio easily in a voice channel for your Discord.js bot. Easy documentations and easy to use.

Picovoice Eagle Node.js binding

Leopard Speech-to-Text engine for web browsers (via WebAssembly)

Get live audio stream data for React Native

React hooks for Micdrop voice conversation client

An Open-source Voice & Video Calling UI Component Based on Tencent Cloud Service.

科大讯飞语音识别 SDK，支持浏览器中实时语音听写功能

Demo for Gemini Live and LlamaIndexTS

Build voice-enabled AI agents with Cloudflare Workers and OpenAI's Realtime API

A React Native Voice Recognition Module

React Hook for OpenAI Whisper API with speech recorder and silence removal built-in.

A library to convert text to speech using the Eleven Labs API

OneBot 工具集，带有点赞、打卡、拍一拍、表情回应和 AI 语音等功能，可独立开关和自由配置

A React component for real-time transcription and voice agent interactions using Deepgram APIs

React hook for Leopard Web SDK

JavaScript SDK for TargetAI WebRTC voice agent communication

React hook for real-time AI voice conversations using OpenAI Realtime API

A React Native wrapper for the Twilio mobile SDK

A custom wrapper for ElevenLabs ConvAI widget that provides a branded embed experience

Ai and Canvas library. Supports ts & js (supports front/back end).

Slang Voice Assistant for E-commerce apps.

Framework for building sophisticated voice apps

MCP server for macOS text-to-speech using the say command

Talknbox VE nodes for n8n (calls, campaigns, contacts, agents, queues, reports, webhooks, system).

Various diagnostics functions to help analyze connections to Twilio and removed DOMError type

This is the client js sdk for cutting-edge Samvyo real-time voice/video cloud.

Falcon Speaker Diarization engine for web browsers (via WebAssembly)

N8N community node for Groq API - Speech-to-Text transcription using Whisper AI. Convert audio to text with high accuracy. Perfect for WhatsApp voice messages, audio files, and voice automation workflows.

asterisk alarm system

Say iMproved - Advanced text-to-speech CLI with custom voice models

Experiment for making video streaming work for discord self bots

React Hook for OpenAI Whisper API with speech recorder and silence removal built-in.

A real-time voice streaming as base-64 string chunks

Wrapper for the ElevenLabs API

Audio / Voice Recorder for React

A powerful TypeScript-based React hook that provides complete audio recording capabilities with pause/resume functionality, recording management, and audio processing

Set of React components that use the Web Speech API to bring voice experience to React applications

Picovoice Rhino React Native binding

React Hook for OpenAI Whisper API with speech recorder and silence removal built-in in Qubby

React Native plugin for adding voice using Spokestack

React Native wrapper for Twilio Programmable Voice SDK

Retell.ai MCP Server - Fork of @abhaybabbar/retellai-mcp-server

``` npm i react-recorder-voice ```

React voice search component with audio visualization, speech recognition, and cross-browser support for Web Speech API. SSR-compatible with Next.js.

JavaScript Web API for Text-to-Speech and Speech-to-Text.

Node.js client for Notify.Events

Alexa Voice Service wrapper for the browser.

Picovoice Cheetah Node.js binding

React component for rendering voice messages in chat-based apps

Klatt formant synthesizer

Adds syntax highlighting, hover tips, and autocomplete to Alexa SFB story files.

React Native component for enhancing app with voice interaction using Alan.AI SDK

Notify.Events node for Node-RED

Lightweight WebRTC browser library that supports video, audio and data channels

VoiceIt's API 2.0 Face + Voice Verification/Identification Node Wrapper

Cartesia implementation for @micdrop/server

A portable replacement for WebRTC's media component

NPM Package to install SDK for Chat, WebRTC Audio, and Video Calls that will land on Cisco Contact Center Agents handling calls using Cisco Jabber or similar in any node-based application.

Low-level Lavalink/NodeLink wrapper.

scanner in web, phonebook in web, autofill otp in web, share web, TextToSpeech in web, Voice Recognition in web, live location tracking in web, detect my location web, wakelock in web, color picker, WhatsappShare, SnapScanner, NetworkMonitor, View360

WebGAL GPT-SoVITS语音合成应用

Voice recognition for node native

A complete framework to facilitate the tracking of user voice time using discord.js

An intuitive and customizable React Native module for playing voice messages seamlessly in chat interfaces. This package offers out-of-the-box components and easy-to-use configurations to integrate voice message playback functionality in your application.

A powerful speech recognition library for React Native applications, enabling real-time speech-to-text transcription.

A customizable and interactive voice UI component for React applications

Picovoice Cobra Node.js binding

Remove list styles in CSS without preventing VoiceOver from announcing them in Safari

Capacitor plugin for voice recording

Multi-Modal Input Library for voice, gesture, and traditional inputs.

Alexa SFB build and deployment module

Pipedream Voiceflow Components

2025-02 Updated fork of react-audio-voice-recorder v2.2.0

An abstraction over P2P video/voice/data connections using WebRTC

Experiment for making video streaming work for discord selfbots

Get live audio PCM stream data then can fft to frequency histogram for React Native, also support wave surfer

A comprehensive React component library for building AI agent interfaces with support for chat, voice, form, media, and coding agents

数字人网关代理SDK，提供完整的数字人交互功能，包含数字人管理、音色管理、会话管理和TTS语音合成

Claude Code plugin for text-to-speech plan narration using ElevenLabs

Node-Red nodes for google-home-notify library. With this node you can cast any String (up to 200 chars) to any google cast device.

A text-to-speech extractor for discord-player

Twilio integration for WeWeb backend services

Voice synthesis library for AITuber OnAir

New version of audio recorder for Vue.js 2. It allows to record, play, download and store records on a server. It is based on vue-audio-recorder which is not longer being supported by the original author (grishkovelli).

React.js component offering mobile and desktop browser voice and video communication. Wraps sip.js with the nitty gritty details required make it work in such environments to help focus on application development.

Interactive text-to-speech CLI with multiple voices using ElevenLabs API

Biblioteca para gravação de áudio com Angular e PO UI que depois converta o áudio gravado em json estruturado.

Unify input from keyboard, gamepad, touch, and voice into logical actions.

Real-time speech analysis with local LLM using multiple concurrent analysis instructions

Forked React Native wrapper for Twilio Programmable Voice SDK

a Telegram bot who can send voice messages via inline mode added by admin with sorting them by numbers of uses

Widget de chat de voz da KOIA para integração fácil em qualquer site

Workspace application API used by Workspace Web Edition

React Native voice recognition module like react-native-voice

An Open-source Voice & Video Calling UI Component Based on Tencent Cloud Service.

Voice AI utilities for home loan assistance with India-specific formatting

React Native wrapper for Twilio Programmable Voice SDK

Text to Speech (Pure Client Side)

TermTalk — terminal chat + commands + AI with Python voice worker

With this adapter you can control ioBroker with voice in many different languages

Experiment for making video streaming work for discord selfbots

A React WebRTC voice chat widget component for Amalgam SaaS

A React/Next.js library for AI assistant widget with floating button, voice call, and chat functionality

A Quill rich text editor module that adds speech-to-text input capabilities

A CLI tool for sending mass lead emails to prospective clients from CSV files with AI-powered personalization

n8n community node for ai-coustics speech enhancement API

Picovoice Rhino Node.js binding

A simple JavaScript speech recognition library.

RNNoise for Unity

Hermes javascript bindings

A Somleng helper library

🐝 Intelligent Claude CLI wrapper with rule injection, AFk background processing, voice interface, and adaptive retry

WebGAL 工具集统一命令行接口

Twilio provider for adonis framework

React Native module for record and playing sound in realtime

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

This library provides Voice Recognition service to fill the form input fields (text, datepicker, textarea, button-click) for Angular application.

React Native Native Voice library for iOS and Android

Experiment for making video streaming work for discord selfbots

React Native wrapper for Gizwits Coze Socket SDK

Alan Voice Cordova plugin

TTS (Text to Speech) for Node and Browser

A JavaScript wrapper aroung the the Hermes protocol.

React Native wrapper for Twilio Programmable Voice SDK

Audio / Voice Recorder for React

React Native component for enhancing app with voice interaction using Alan.AI SDK

Alan Button Web component

An Open-source Voice & Video Calling UI Component Based on Tencent Cloud Service.

A simple audio mixer for Discord voice bots using discord.js/voice.

React Native specific components and utilities for multimodal UI

Node-Red nodes for google-home-notifier-offline library. With this node you can cast any String (up to 200 chars) to any google cast device.

React Native module for IBM Watson services

Node JS Interface to the VoiceIt REST Api

fork of [vocode](https://github.com/vocodedev/vocode-react-sdk)

Node Red module for the Wazo Platform API

Node-RED nodes for sipgate.io that offer a convenient way to build communications applications (e.g. IVR, lookup dependent call routing) on top of the sipgate API.

An Open-source Voice & Video Calling UI Component Based on Tencent Cloud Service.

VoiceTest: a real-time voice-enabled Discord bot that streams speech to OpenAI GPT-4o and plays AI-driven voice responses.

React Hook for OpenAI Whisper API with speech recorder and silence removal built-in in Qubby

Trillet Web SDK for real-time audio communication with AI agents

Voice WebRTC sfu sagas.

MCP server that converts text to speech using OpenAI for transformation and ElevenLabs for voice synthesis

Easily convert text to speech using Google Wavenet voices on Node-RED.

React Native module for IBM Bluemix services