Skip to main content

🖐️🎤 Micdrop

Real-time voice conversations with AI in the browser

Integrate a powerful voice mode in your webapp with a few lines of code using Micdrop. Use provided AI integrations (agents, STT, TTS) or build your own. Build the best UX with our SDK.

Start Building (5 min)View on GitHub

Free, open source (MIT). Bring your own API keys (BYOK).

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')
})

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.

🎙️ Mic🔈 SpeakerClientServerSTTAgentTTS
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

Essential packages for browser and server-side implementation

@micdrop/client@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

Utilities

React hooks and utilities for seamless frontend integration

@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.

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.

Mistral

Agent (LLM)

French LLM for conversational AI

Gladia

Speech-to-Text

French STT with 90+ languages

Gradium

Text-to-Speech

French TTS with natural voices

100% open-source stack. No data leaves the EU. 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 ▶️