Vapi
docs.vapi.ai
AI & Machine LearningVapi is the platform to build, test and deploy voice agents in minutes rather than months.
llms.txt
Vapi
Instructions for AI Agents
- For clean Markdown of any page, append
.mdto the page URL - For a complete documentation index, see https://docs.vapi.ai/llms.txt
- For full documentation content in one file, see https://docs.vapi.ai/llms-full.txt
- For section-specific indexes, append
/llms.txtto any section URL - For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server
Docs
- Introduction: Build voice AI agents that can make and receive phone calls
- Phone calls: Learn to make your first phone call with a voice agent
- Web calls: Build voice interfaces and backend integrations using Vapi's Web and Server SDKs
- Guides: Explore real-world, cloneable examples to build voice agents with Assistants and Squads
- Composer: Build and configure voice AI agents through natural conversation
- Vapi CLI: Command-line interface for building voice AI applications faster
- Assistants quickstart: Build your first assistant and make a phone call in minutes
- Transient vs permanent configurations: Learn to choose between inline and stored assistant configurations
- Variables: Personalize assistant messages with dynamic and default variables
- Multilingual support: Configure multilingual voice AI agents with automatic language detection, cross-language conversation, and localized voices
- Personalization with user information: Add customer-specific information to your voice assistant conversations
- Voice formatting plan: Format LLM output for natural-sounding speech
- Flush syntax: Force immediate voice transmission with VAPI's flush syntax for real-time interactions
- Background messages: Silently update chat history with background messages
- Idle messages: Keep users engaged during conversation pauses
- Assistant hooks: Automate actions on call events and interruptions
- Background speech denoising: Filter out noise and background speech while users are talking
- Pronunciation dictionaries: Control how your AI assistant pronounces specific words and phrases
- Email address reading: Get your voice agent to collect, read back, and confirm email addresses clearly
- Speech configuration: Control when your assistant starts and stops speaking
- Voice pipeline configuration: Complete guide to configuring VAPI's voice pipeline for optimal conversation timing and interruption handling
- Voice fallback configuration: Configure fallback voices that activate automatically if your primary voice fails.
- Transcriber fallback configuration: Configure fallback transcribers that activate automatically if your primary transcriber fails.
- OpenAI Realtime: Build voice assistants with OpenAI's native speech-to-speech models for ultra-low latency conversations
- Provider Keys: Bring your own API keys to Vapi.
- Introduction to Tools: Extend your assistant's capabilities with powerful function calling tools.
- Default Tools: Adding Transfer Call, End Call, Dial Keypad, and API Request capabilities to your assistants.
- Voicemail Tool: Learn how to use the assistant-controlled voicemail tool for flexible voicemail handling
- Custom Tools: Learn how to create and configure Custom Tools for use by your Vapi assistants.
- Code Tool: Execute custom TypeScript code directly within your assistant without setting up a server.
- Client-side Tools (Web SDK): Handle tool-calls in the browser without a server URL
- Tool rejection plan: Prevent unintended tool calls using conditions based on conversation state
- Static variables and aliases: Inject server-controlled values into tool calls without LLM involvement, and chain values across tool calls deterministically.
- Custom tools troubleshooting: Resolve common issues with custom tool integrations
- Google Calendar Integration: Connect your assistant to Google Calendar for seamless appointment scheduling and availability checking.
- Google Sheets Integration: Connect your assistant to Google Sheets for seamless data entry.
- Slack Integration: Connect your assistant to Slack for seamless message sending.
- GoHighLevel Integration: Connect your assistant to GoHighLevel for seamless appointment scheduling, contact creation, and availability checking.
- Introduction to Knowledge Bases: Learn how to create and integrate custom knowledge bases into your AI assistants.
- Using the Query Tool for Knowledge Bases: Learn how to configure and use the query tool to enhance your AI assistants with custom knowledge bases.
- Custom Knowledge Base: Create and implement your own knowledge base server for full control over document retrieval
- Tool Arguments Encryption: Learn to encrypt tool arguments and protect sensitive data
- Deepgram Keywords and Keyterm Prompting: Boost STT accuracy for domain words and phrases
- Custom voices: Use a custom voice with your preferred provider
- ElevenLabs: Set up a custom ElevenLabs voice in Vapi
- PlayHT: Set up a custom PlayHT voice in Vapi
- Custom transcriber: Integrate your own transcription service with Vapi
- Custom TTS integration: Learn to integrate your own text-to-speech system with VAPI
- Fine-tuned OpenAI models: Use Another LLM or Your Own Server
- Connecting Your Custom LLM to Vapi: A Comprehensive Guide
- Custom LLM Tool Calling Integration
- Appointment scheduling assistant: Build a voice AI appointment scheduling assistant with Google Calendar integration, availability checking, and automated confirmations using Vapi Assistants.
- Lead qualification assistant: Build a voice AI outbound sales assistant with BANT data capture, CRM integration, objection handling, and automated follow-ups using Vapi Assistants.
- Inbound customer support: Build a voice AI banking support agent with tools for account lookup, balance and transaction retrieval.
- Web Snippet: Easily integrate the Vapi Voice Widget into your website for enhanced user interaction.
- Documentation agent: Build a voice assistant that answers questions about your docs
- Customer support escalation system: Build a voice AI customer support system with dynamic escalation that routes calls based on customer data, issue type, and real-time agent availability using transfer tools and webhooks.
- Multilingual support agent: Build a multilingual voice AI customer support agent with automatic language detection, native voices, and comprehensive tools for international customer service
- Evals quickstart: Get started with AI agent testing in 5 minutes
- Advanced eval testing: Master testing strategies and best practices for production AI agents
- Simulations quickstart: Test your AI assistants with realistic AI-powered callers
- Simulations advanced: Master testing strategies and best practices for AI voice agent simulations
- Boards quickstart: Create custom analytics dashboards in minutes
- Structured outputs quickstart: Get started with structured data extraction in 5 minutes
- Structured outputs examples: Real-world examples and templates for common use cases
- Scorecard quickstart: Automatically grade calls against KPIs using structured outputs
- Monitoring quickstart: Set up automated quality monitoring for your voice AI agents
- Configuring Inbound and Outbound Calls for Squads: Configuring assistants for inbound/outbound calls.
- Introduction to Squads (Multi-Assistant Conversations): Use Squads to handle complex workflows and tasks.
- Handoff tool: Transfer the call to another assistant, squad, or dynamically determined destination.
- Passing data between assistants: Three approaches for forwarding context to the next assistant in a squad — when to use each, and what each one costs.
- Clinic triage with handoff tools: Build a multi-assistant clinic experience with specialized assistants for triage, emergency handling, and scheduling using handoff tools.
- Clinic triage and scheduling squad: Build a multi-assistant clinic experience with specialized assistants for triage, emergency handling, and scheduling using Squads.
- E‑commerce order management squad: Build a multi-assistant experience for order tracking, returns processing, and VIP handling using Squads.
- Property management routing squad: Build a property management Squad with a router assistant plus maintenance and leasing specialists for accurate transfers.
- Multilingual support squad: Build a Squad with dedicated English, Spanish, and French assistants and a language selection entrance flow.
- Silent Handoffs
- Voice AI Prompting Guide: How to write effective prompts for voice AI assistants
- Debugging voice agents: Learn to identify, diagnose, and fix common issues with your voice assistants and workflows
- Enterprise environments (DEV/UAT/PROD): Promotion and configuration management for assistants and squads
- IVR Navigation: How to navigate IVR menu systems effectively
- Test Suites: End-to-end test automation for AI voice agents
- Chat Testing: Automated text-based testing for AI agents
- Voice Testing: Automated voice call testing for AI voice agents
- Creating Free Phone Numbers: Creating free phone numbers on the Vapi platform.
- Inbound SMS: Let agents auto-start chats from incoming text messages (US only)
- Import number from Twilio: Import a new or existing number from Twilio
- Import number from Telnyx: Import and use your Telnyx numbers with Vapi
- SIP introduction: Make SIP calls to your Vapi assistant
- SIP Trunking: How to integrate your SIP provider with Vapi
- SIP networking and firewall configuration: Learn to configure your network to allow SIP signalling and media traffic with Vapi
- Twilio SIP Integration: How to integrate Twilio SIP with Vapi
- Telnyx SIP integration: How to integrate SIP Telnyx to Vapi
- Zadarma SIP Integration: How to integrate SIP Zadarma to Vapi
- Plivo SIP Integration: Learn to connect your Plivo SIP trunk to Vapi for inbound and outbound calls
- Amazon Chime SDK SIP Integration: How to integrate Amazon Chime SDK Voice Connector with Vapi
- Troubleshoot SIP trunk credential errors: Learn to resolve gateway creation failures when setting up a BYO SIP trunk
- Phone Number Hooks
- Phone Calling: Learn how to create and configure phone numbers with Vapi
- Outbound Calling: Learn how to send outbound calls from Vapi.
- WebSocket Transport: Stream audio directly via WebSockets for real-time, bidirectional communication
- Live Call Control
- Customer Join Timeout: Set maximum time for users to join web calls before automatic termination
- Voicemail Detection
- Call Forwarding
- Assistant-based warm transfer: Use AI assistants to facilitate call transfers
- Dynamic call transfers: Learn how Vapi's dynamic call transfers work and explore implementation patterns for intelligent call routing.
- Call Handling with Vapi and Twilio
- Debug call forwarding drops: Learn to troubleshoot calls that drop immediately after initiating transfer
- Call queue management with Twilio: Build a call queue system using Twilio to handle large volumes of calls while respecting Vapi concurrency limits, ensuring no calls are dropped.
- Understanding Call Concurrency: Learn how concurrency slots work, how to stay within the default limit, and how to raise capacity for larger campaigns.
- Call ended reasons: All possible call ended reason codes and what they mean.
- Troubleshoot call errors: Learn to diagnose failed calls based on what the caller experienced.
- Call analysis: Summarize and evaluate calls automatically
- Call recording, logging and transcribing: Learn how to configure artifact plans to record calls, generate transcripts, and store logs for analysis
- Outbound campaigns quickstart: Build a simple personalized outbound campaign that conducts post-service feedback and follow-up calls to improve customer experience
- Outbound campaigns overview: Learn how to efficiently schedule calls, manage recipients, analyze performance metrics, and review detailed call logs and transcripts with Vapi's Outbound Call Campaigns
- Chat quickstart: Build your first text-based conversation with a Vapi assistant in 5 minutes
- Streaming chat: Build real-time chat experiences with token-by-token responses like ChatGPT
- Non-streaming chat: Build reliable chat integrations with complete response patterns for batch processing and simple UIs
- OpenAI compatibility: Seamlessly migrate existing OpenAI integrations to Vapi with zero code changes
- Session management: Maintain conversation context using previousChatId vs sessionId
- Variable substitution in sessions: Learn how template variables behave with sessions and chats
- SMS chat: Enable text-based conversations with assistants via SMS messaging
- Web widget: Add AI chat and voice capabilities to any website with a simple embeddable widget
- Server URLs: Learn how to set up your server to receive and respond to messages from Vapi.
- Setting server URLs: Learn about where you can set server URLs to handle call events.
- Server events: Learn about different events that can be sent to a Server URL.
- Spam call rejection: Screen inbound calls and reject known spam using your Server URL
- Developing locally: Learn how to receive server events in your local development environment.
- Server authentication
- Workflows quickstart: Build a simple agent that greets users and gathers basic information using Vapi workflows.
- Workflows overview: Learn to create robust, deterministic conversation flows with a visual builder.
- Appointment scheduling workflow: Build a voice AI appointment scheduling workflow with calendar integration, availability checking, and automated confirmations using Vapi's workflow builder.
- Lead qualification workflow: Build a voice AI outbound sales workflow with lead qualification, CRM integration, and automated follow-up using Vapi's visual workflow builder.
- Clinic triage and scheduling workflow: Build a voice AI clinic workflow with medical triage protocols, appointment booking, and emergency routing using Vapi's visual workflow builder.
- E-commerce order management workflow: Build a voice AI e-commerce workflow with order tracking, return processing, and customer support automation using Vapi's visual workflow builder.
- Property management call routing: Build a voice AI property management system with dynamic call routing that determines destinations based on tenant verification, inquiry type analysis, and real-time agent availability using workflow API requests.
- Multilingual support workflow: Build a multilingual voice AI customer support workflow with language selection, dedicated conversation nodes, and cultural context using Vapi's workflow builder.
- Frequently Asked Questions: Frequently asked questions about Vapi.
- Core Models: Learn about the three core components to Vapi's voice AI pipeline.
- Orchestration Models: Learn about the real-time models Vapi runs on top of STT, LLM, and TTS.
- Vapi Voices: Our curated selection of high-quality voices
- Legacy voice migration guide: Legacy Vapi Voices were retired on March 1, 2026. Here's what changed and how to update if needed.
- ElevenLabs: How Vapi Integrates Text-to-Speech Platforms?
- PlayHT
- Azure
- OpenAI
- Cartesia
- LMNT
- Minimax: Configure Minimax TTS voices and word-level subtitle timing
- RimeAI
- Deepgram
- Inworld
- OpenAI: What is OpenAI?
- Azure OpenAI: Use custom Azure OpenAI instances with your own rate limits and configurations
- Anthropic Bedrock: Use Anthropic Claude models via AWS Bedrock with your own AWS resources
- Gemini by Google: What is Gemini?
- Groq: What is Groq?
- DeepInfra: DeepInfra is a provider for Vapi.
- Perplexity: What is Perplexity.ai?
- TogetherAI: TogetherAI is a provider for Vapi.
- OpenRouter: What is OpenRouter?
- Deepgram: What is Deepgram?
- Gladia
- Speechmatics
- Talkscriber: What is Talkscriber?
- AssemblyAI
- AWS S3: Store recordings of chat conversations in AWS S3
- GCP Cloud Storage: Store recordings of chat conversations in GCP Cloud Storage
- Cloudflare R2: Store recordings of chat conversations in Cloudflare R2
- Supabase S3 Storage: Store recordings of chat conversations in Supabase Storage
- Langfuse Integration with Vapi: Integrate Vapi with Langfuse for enhanced voice AI telemetry monitoring, enabling improved performance and reliability of your AI applications.
- Voiceflow: Vapi x Voiceflow
- ChatDash Integration with Vapi: ChatDash is a white-label dashboard platform that integrates with Vapi to provide analytics, call logs, and Stripe billing for AI agent agencies.
- Vapify Integration with Vapi: Vapify is a white-label dashboard for Vapi. It helps you turn your agency into a voice AI powerhouse—without writing a single line of code.
- Voicerr AI - Whitelabel AI Voice Agents: Voicerr AI is a Vapi-powered voice platform that lets agencies brand dashboards, automate billing, launch campaigns, and run full call-center operations at unlimited scale.
- VoiceAIWrapper Integration with Vapi: White-Label Vapi Integration | Launch Your Voice AI Agency in 30 Minutes
- Sympana Connector: Native GoHighLevel automation for Vapi agents
- Support: We are open to all kinds of help inquiry, feedback and feature request, help inquiry.
- How to Report Issues Effectively: Learn how to structure your issue reports for fast and accurate resolution
- Vapi Enterprise: Build and scale with Vapi.
- Definitions: Useful terms and definitions for Vapi & voice AI applications.
- RSS Feed: Stay updated with the latest incidents from Vapi or third party providers
- Data Flow: Understand how data flows through Vapi when using custom storage and custom models
- JWT Authentication: Secure API authentication guide
- Recording consent plan: Learn how to configure recording consent plans to ensure compliance with privacy laws and regulations
- GDPR Compliance: Learn how Vapi ensures GDPR compliance for its voice assistant platform.
- HIPAA Compliance: Learn how to ensure privacy when using Vapi's voice assistant platform.
- Retrieve call artifacts: Download recordings and call logs from Vapi's private storage using authenticated, short-lived URLs.
- PCI Compliance: Ensure secure payment data handling while using Vapi’s voice assistant platform.
- Proxy server guide: Keep assistant configs and API keys on your backend. Route Web SDK calls through your proxy.
- Static IP addresses: Whitelist Vapi IP addresses
- TCPA Consent Guide: Understanding consent requirements for outbound calls using Vapi's voice agent service.
- Model Context Protocol (MCP) Integration: Connect your assistant to dynamic tools through MCP servers for enhanced capabilities.
- Vapi MCP Server: Connect Vapi to AI assistants with Model Context Protocol (MCP)
- Ecosystem: Find all of our resources here.
- Project integration: Initialize Vapi in your existing projects with intelligent auto-detection
- MCP integration: Turn your IDE into a Vapi expert with Model Context Protocol
- Local webhook testing: Forward webhooks to your local development server with vapi listen
- Authentication management: Manage multiple Vapi accounts and environments with the CLI
- What's New?
API Docs
- API reference > Assistants List Assistants
- API reference > Assistants Create Assistant
- API reference > Assistants Get Assistant
- API reference > Assistants Delete Assistant
- API reference > Assistants Update Assistant
- API reference > Squads List Squads
- API reference > Squads Create Squad
- API reference > Squads Get Squad
- API reference > Squads Delete Squad
- API reference > Squads Update Squad
- API reference > Calls List Calls
- API reference > Calls Create Call
- API reference > Calls Get Call
- API reference > Calls Delete Call
- API reference > Calls Update Call
- API reference > Chats List Chats
- API reference > Chats Create Chat
- API reference > Chats Get Chat
- API reference > Chats Delete Chat
- API reference > Chats Create Chat (OpenAI Compatible)
- API reference > Campaigns List Campaigns
- API reference > Campaigns Create Campaign
- API reference > Campaigns Get Campaign
- API reference > Campaigns Delete Campaign
- API reference > Campaigns Update Campaign
- API reference > Sessions List Sessions
- API reference > Sessions Create Session
- API reference > Sessions Get Session
- API reference > Sessions Delete Session
- API reference > Sessions Update Session
- API reference > Phone Numbers List Phone Numbers
- API reference > Phone Numbers Create Phone Number
- API reference > Phone Numbers Get Phone Number
- API reference > Phone Numbers Delete Phone Number
- API reference > Phone Numbers Update Phone Number
- API reference > Tools List Tools
- API reference > Tools Create Tool
- API reference > Tools Get Tool
- API reference > Tools Delete Tool
- API reference > Tools Update Tool
- API reference > Files List Files
- API reference > Files Upload File
- API reference > Files Get File
- API reference > Files Delete File
- API reference > Files Update File
- API reference > Structured Outputs List Structured Outputs
- API reference > Structured Outputs Create Structured Output
- API reference > Structured Outputs Get Structured Output
- API reference > Structured Outputs Delete Structured Output
- API reference > Structured Outputs Update Structured Output
- API reference > Structured Outputs Run Structured Output
- API reference > Insight Get Insights
- API reference > Insight Create Insight
- API reference > Insight Get Insight
- API reference > Insight Delete Insight
- API reference > Insight Update Insight
- API reference > Insight Run Insight
- API reference > Insight Preview Insight
- API reference > Eval List Evals
- API reference > Eval Create Eval
- API reference > Eval Get Eval
- API reference > Eval Delete Eval
- API reference > Eval Update Eval
- API reference > Eval Get Eval Run
- API reference > Eval Delete Eval Run
- API reference > Eval List Eval Runs
- API reference > Eval Create Eval Run
- API reference > Observability Scorecard Get Scorecard
- API reference > Observability Scorecard Delete Scorecard
- API reference > Observability Scorecard Update Scorecard
- API reference > Observability Scorecard List Scorecards
- API reference > Observability Scorecard Create Scorecard
- API reference > Provider Resources List Provider Resources
- API reference > Provider Resources Create Provider Resource
- API reference > Provider Resources Get Provider Resource
- API reference > Provider Resources Delete Provider Resource
- API reference > Provider Resources Update Provider Resource
- API reference > Analytics Create Analytics Queries
- Webhooks Server Message
- Webhooks Client Message
OpenAPI Specification
The raw OpenAPI 3.1 specification for this API is available at:
Related
Perplexity AI is an AI-powered search engine that provides direct answers to user queries by leveraging large language models.
/llms.txt
1,173 tokens
/llms-full.txt
40,087 tokens
AI & Machine Learning
Shop Dell's laptops, Monitors, Computers, Storage Solutions & Servers for your home and business. Buy online!
/llms.txt
8,533 tokens
AI & Machine Learning
Create the most realistic speech with our AI audio in 1000s of voices and 32 languages. Pioneering research in Text to Speech and AI Voice Generation
/llms.txt
23,168 tokens
/llms-full.txt
1,020,683 tokens
AI & Machine Learning
Get started with the Model Context Protocol (MCP).
/llms.txt
3,315 tokens
/llms-full.txt
223,365 tokens
AI & Machine Learning
The Voice AI Platform: TTS Models, Voice Agents, & More.
/llms.txt
1,738 tokens
/llms-full.txt
56,923 tokens
AI & Machine Learning