Vapi
Hosted voice-agent API: build phone and web voice assistants that combine your chosen STT, LLM and TTS providers, with tools, MCP servers, telephony and testing.
Tags
Description
Configure assistants (transcriber, model, voice, tools) via dashboard or API and deploy them on phone numbers, SIP or the web. Assistants can import tools from any MCP server at call time (Streamable HTTP by default; Vapi sends X-Call-Id/X-Chat-Id headers), and Vapi also publishes its own MCP server exposing the Vapi API. Pricing (as of 2026-10-23): pay-as-you-go $0.05/min Vapi hosting plus provider costs passed through without markup, $5 free credits, 4 concurrent calls; paid success packages (Core, Pro from $999/month minimum, Premier) add concurrency, retention, ZDR and SLAs. Docs ship llms.txt and markdown pages (append .md) plus a docs MCP server.
Agent access
Related
- LiveKit Agents: Open-source Python (and JS) framework for realtime voice and video agents over WebRTC, with STT/LLM/TTS plugins, telephony, turn detection, MCP tools and tests.
- Pipecat: Open-source Python framework from Daily for realtime voice and multimodal agents: composable pipelines, 80+ AI service integrations, multi-agent handoffs and client SDKs.
- ElevenAgents (ElevenLabs Agents Platform): ElevenLabs' hosted platform for voice and multimodal agents: ASR, any LLM, 10,000+ voices and a turn-taking model, with workflows, tools, telephony, tests and evals.
- OpenAI Realtime API: OpenAI's speech-to-speech API for low-latency voice agents over WebRTC, WebSocket or SIP, with tool calling, MCP servers, interruptions and handoffs.
Guides & comparisons
- LiveKit Agents vs Pipecat vs OpenAI Realtime vs ElevenAgents vs Vapi: building voice agents (Comparison): Five ways to give an agent a voice compared: two open-source realtime frameworks (LiveKit Agents, Pipecat), a speech-to-speech model API (OpenAI Realtime) and two hosted voice-agent platforms (ElevenAgents, Vapi). Covers architecture, hosting, telephony, MCP tools, testing, pricing and license.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)