🖐️🎤 Micdrop

Real-time voice conversations with AI, in the browser and on mobile

Integrate a powerful voice mode in your webapp or your React Native app with a few lines of code using Micdrop. One server, the same call on every platform. Use provided AI integrations (agents, STT, TTS) or build your own.

Start Building (5 min) View on GitHub

Free, open source (MIT). Bring your own API keys, or run the models on your own machine.

npm install @micdrop/client

import { Micdrop } from '@micdrop/client'

// Start a voice conversation
Micdrop.start({
  url: 'wss://your-server.com/'
})

// Listen for events
Micdrop.on('StateChange', (state) => {
  console.log('Conversation:', state.conversation)
  console.log('isAssistantSpeaking:', state.isAssistantSpeaking)
})

Micdrop.on('EndCall', () => {
  console.log('Call ended by assistant')
})

npm install @micdrop/server \
  @micdrop/openai \
  @micdrop/gladia \
  @micdrop/elevenlabs

import { MicdropServer } from '@micdrop/server'
import { OpenaiAgent } from '@micdrop/openai'
import { GladiaSTT } from '@micdrop/gladia'
import { ElevenLabsTTS } from '@micdrop/elevenlabs'
import { WebSocketServer } from 'ws'

const wss = new WebSocketServer({ port: 443 })

wss.on('connection', (socket) => {
  // Handle voice conversation
  new MicdropServer(socket, {
    firstMessage: 'How can I help you today?',

    agent: new OpenaiAgent({
      apiKey: process.env.OPENAI_API_KEY,
      systemPrompt: 'You are a helpful assistant'
    }),

    stt: new GladiaSTT({
      apiKey: process.env.GLADIA_API_KEY
    }),

    tts: new ElevenLabsTTS({
      apiKey: process.env.ELEVENLABS_API_KEY,
      voiceId: process.env.ELEVENLABS_VOICE_ID
    })
  })
})

How It Works

Micdrop orchestrates a complete voice conversation pipeline. Watch how voice data flows through each component in real-time, from your microphone to AI responses and back to your speakers.

Audio

Message chunks

Messages

🎤 Voice Input

Client captures microphone input, VAD detects speech, and audio chunks are sent to the server for processing.

🤖 AI Processing

Server orchestrates STT transcription, AI agent reasoning, tool calls, and TTS generation for natural responses.

🔊 Voice Output

Generated audio streams back to the client for playback, with full support for interruptions and real-time interaction.

📦 Packages

Modular architecture with specialized packages for different use cases

Core Packages

One server, and the client for the platform you are building for

@micdrop/web @micdrop/react-native @micdrop/server

AI Integrations

Ready-to-use integrations with popular AI providers

@micdrop/openai @micdrop/ai-sdk @micdrop/elevenlabs @micdrop/cartesia @micdrop/gradium @micdrop/mistral @micdrop/gladia

Local Models

Transcription and voice that run inside your Node process. The audio stays on the machine.

@micdrop/whisper @micdrop/kokoro @micdrop/piper @micdrop/pocket-tts

Utilities

React hooks that re-render your components as the call state changes, in the browser and in React Native

@micdrop/react

Just call start() and your app has complete voice AI.

Micdrop handles all the complexity for you.

Low Latency

Optimized for minimal delay with streaming audio processing, voice activity detection (VAD), and efficient WebSocket communication for near real-time voice interactions.

AI Provider Agnostic

Choose the best AI providers for your use case. Mix and match OpenAI, ElevenLabs, Cartesia, Mistral, Gladia, and more. Build custom integrations using our abstract interfaces.

Runs On Your Machine

The local packages run the speech models inside your Node process and the agent on Ollama, so the whole conversation works offline, with no API key and no audio leaving the machine.

Web and Mobile

The browser and React Native clients are two thin layers over the same engine, so a call behaves the same on a laptop and on a phone, against the server you already run. Microphone permission, audio session and echo cancellation are handled for you.

Developer Experience

Built with TypeScript for excellent DX. Comprehensive documentation, React hooks, demo applications, and detailed examples to get you started quickly.

🇫🇷 🇪🇺

Build Sovereign Voice AI

Micdrop is the perfect solution to build sovereign voice AI applications, especially in French. Combine European AI providers to keep your data and infrastructure fully within EU borders.

100% open-source stack. Your data stays in the EU, or on your own machine with local models. Full GDPR compliance.

Learn more about sovereign voice AI

🎥 See it in Action

Watch the creator explain Micdrop and voice AI technology

Watch Demo Video ▶️