Vapi 发布 Vapi CLI：为构建语音 AI 智能体提供最佳开发者体验

Vapicon 2026 is coming

TL;DR: We've built the Vapi CLI to bring world-class developer experience to your terminal and IDE. Drop Vapi into any project with one command, debug webhooks locally without ngrok, and turn your IDE into a Vapi expert with MCP integration.

Building voice AI agents shouldn't require constantly switching between your terminal, browser, and IDE. You shouldn't need to set up ngrok tunnels just to test webhooks. And your IDE definitely shouldn't hallucinate Vapi APIs that don't exist.

That's why we built the Vapi CLI - a command-line interface designed from the ground up to give developers the best possible experience when building voice AI applications.

The Vapi CLI gives you complete control over your voice AI infrastructure without leaving your terminal:

Every feature in the Vapi dashboard is now available as a simple command. No more context switching between terminal and browser when you're in the flow.

Drop Vapi Into Any Project

The magic happens with vapi init. Point it at any codebase and it automatically:

Detects your tech stack - React, Vue, Next.js, Python, Go, Flutter, React Native, and dozens more; Installs the appropriate Vapi SDK for your framework; Generates working code examples tailored to your project structure; Sets up environment configuration templates

No more copy-pasting from docs or figuring out integration patterns. You get production-ready code that follows best practices for your specific setup.

Here's something that will change how you develop with Vapi: MCP (Model Context Protocol) integration.

Run vapi mcp setup and your IDE's AI assistant (Cursor, Windsurf, VSCode with Copilot) gains complete, accurate knowledge of Vapi's APIs, features, and best practices.

Before MCP:

AI suggests non-existent Vapi methods; You waste time debugging hallucinated code; Documentation lookups break your flow

After MCP:

AI knows exactly how Vapi works; Code suggestions are accurate and current; Your development velocity increases dramatically

Ask your IDE: "How do I create a voice assistant that transfers calls to a human?" and get real, working Vapi code instead of guesswork.

Testing webhooks during development has always been painful. Not anymore.

That's it. The CLI starts a local server that receives all your Vapi webhook events and forwards them to your development server in real-time.

What you get:

Instant webhook testing without external tunnels; Real-time event logging for debugging; Automatic request forwarding to any local endpoint; No more ngrok setup or configuration

Built for Production

The CLI isn't just a development tool - it's designed for your entire workflow:

Whether you're prototyping your first voice agent or managing production campaigns with thousands of calls, the CLI scales with your needs.

That's it. You're ready to build voice AI agents with the best developer experience possible.

The Vapi CLI is just the beginning. We're building toward a future where voice AI development is as smooth and intuitive as any other part of your stack.

Stop context switching. Start shipping voice AI agents faster than ever before.

The Vapi CLI is available now. Install it, try it, and let us know what you think. We're just getting started.

Table of Contents

GPT-Live is now in beta for every Vapi customer

Have your personal assistant make the call you keep putting off

Vapi for CX: own every layer, improve every week

Fast decisions alongside voice AI: early experiments with Jev

Campaigns, rebuilt: scale outbound calling with Vapi

Vapi simulations: test for every type of caller

Introducing Vapi Model Intelligence: model recommendations backed by production data

Introducing Vapi Monitoring

Vibe code voice agents

Your Voice Agents Need Tests. Now They Have Them.

Structured Outputs: Extract validated data from voice AI calls

Introducing Squads: Teams of Assistants

Real-time STT vs. Offline STT: Key Differences Explained

Introducing Vapi Workflows

Make your voice agents also chat with Vapi’s new Chat API

What Is ACD? An Introduction to Automatic Call Distribution

Tacotron 2 for Developers

Vapi x LiveKit Turn Detection

5 Days, 5 Features: Sneak Peek into the Future of Vapi

Introducing Vapi Voices

Vapi x Cartesia: Ultra-Realistic Voice AI with Sonic 2.0