Catalog Systems Voice agent platforms Vapi

Vapi

https://vapi.ai/

Voice-AI developer platform — STT + LLM + TTS pipelines wired to telephony (Twilio / SIP). Used to build outbound + inbound phone agents at scale. Raised $20M Series A from Bessemer + Y Combinator (Dec 2024) at $130M valuation; revenue reported >$10M ARR by Q1 2025.

Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 47 cited facts, 3 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Type
Developer platform for AI voice agents (programmable telephony) vendor fix
Tier
T1
Section
Voice agent platforms
Created
2023 (YC W23) vendor fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
GitHub
github.com/VapiAI (SDKs only) repo fix
Pricing
Per-minute usage ($0.05/min base + provider passthrough) vendor fix
Funding
$20M Series A Dec-2024 (Bessemer); $130M val third-party fix
Freshness
2026-10-26 fix
Layer
agent-infra repo fix
Licensing
commercial vendor fix
Deployment locus
cloud vendor fix
Platform vs product
platform vendor fix
Accelerator
yc-w21 third-party fix
SDK languages
csharp, go, java, python, rest, ruby, typescript vendor fix
Protocols
mcp-client, mcp-server vendor fix

When to use

Optimised for: Building phone-call voice agents quickly with composable STT/LLM/TTS

Anti-fit: Telephony-centric — not for in-app voice UX; per-minute pricing scales fast at high volume

Pros & cons

Pros

Category-leading mindshare; Bessemer-backed; SOC 2 + HIPAA; mature webhooks + SDKs.

Cons

Per-minute economics at scale; provider-passthrough means triple vendor exposure (STT + LLM + TTS).

Claims & capabilities

$20M Series A Dec-2024 (Bessemer lead); >$10M ARR reported Q1 2025; YC W23

Technical surface

API surface
REST API; SDKs (Python, JS, React); webhooks
Backend storage
Call state in Vapi-managed DB; transcripts retained per config
Deployment
Cloud-managed; private deployments on Enterprise tier
Embedding model
not applicable — not a memory product
Multi-tenancy
Multi-tenant cloud; Enterprise dedicated tier
MCP
yes — Vapi MCP server (remote https://mcp.vapi.ai/mcp, Streamable HTTP; VapiAI/mcp-server, MIT); assistants can also call MCP tools
A2A
searched not found
OpenTelemetry
searched not found

Compare Vapi with…

Alternatives to Vapi → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other voice agent platforms in the catalog, ranked by inbound references.

  • Cartesia Sonic T1

    Cartesia's Sonic TTS — state-space-model-based voice generation, lowest published TTS latency (~40ms). Cartesia raised $64M Series A Q1 2025 (Index + Lightspeed); founded by Mamba authors. Agent platform layer ('Cartesia Line') wraps Sonic with telephony + LLM.

  • LiveKit Agents T1

    LiveKit Agents — agent framework built on LiveKit's open-source WebRTC media server. LiveKit raised $45M Series B Sep-2024 ($300M val). Powers OpenAI Realtime API's WebRTC transport (LiveKit is the substrate OpenAI chose). Agents framework formally launched 2024.

  • ElevenLabs Conversational AI (now ElevenAgents) T1

    ElevenLabs launched Conversational AI Nov-2024 — STT + LLM + their own market-leading TTS in one pipeline. Combines vendor's voice cloning + multilingual TTS strengths with hosted call orchestration. ElevenLabs raised $180M Series C Jan-2025 at $3.3B val. As of 2026-10 ElevenLabs markets the platform as ElevenAgents.

  • OpenAI Realtime API T1

    OpenAI's Realtime API for native speech-to-speech multimodal interaction with GPT-4o — launched Oct 2024 (DevDay). Skips the STT → LLM → TTS pipeline by passing speech directly to GPT-4o. The platform substrate that Vapi/Retell/Bland integrate as one of their LLM choices.

  • Pipecat (Daily) T1

    Open-source Python framework for real-time voice + multimodal AI agents, maintained by Daily.co. Pipeline-style architecture (STT → context → LLM → TTS) wired over WebRTC. The OSS substrate that many of the voice platforms build on or compose with.

  • Hume EVI T1

    Hume's Empathic Voice Interface (EVI) — voice agent platform with vocal-affect understanding, using Hume's proprietary speech-prosody models. Hume will shut down the EVI and TTS APIs on 2026-11-13 (announced in its docs). Hume raised $50M Series B Mar-2024 (EQT).

Sources (46 cited facts, 3 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • MCP support “Tool-calling supports MCP servers (caller-side)” → “yes — Vapi MCP server (remote https://mcp.vapi.ai/mcp, Streamable HTTP; VapiAI/mcp-server, MIT); assistants can also call MCP tools” source
    #258

Related systems

References (16)

  • Anthropic Claude (foundation models) integrates with · depends on at runtime — adjacent-infrastructure cell: Twilio / Vonage SIP; Deepgram + Cartesia + Eleven STT/TTS; Anthropic / OpenAI LLMs
  • Anyscale integrates with — Vapi docs list Anyscale as a provider/integration. (verified 2026-10-29)
  • Cartesia Sonic integrates with — Vapi docs list Cartesia Sonic as a provider/integration. (verified 2026-10-29)
  • DeepSeek R1 / V3 family integrates with — Vapi docs list DeepSeek R1 / V3 family as a provider/integration. (verified 2026-10-29)
  • ElevenLabs Conversational AI (now ElevenAgents) integrates with — Vapi docs list ElevenLabs Conversational AI as a provider/integration. (verified 2026-10-29)
  • Google Gemini 3 family integrates with — Vapi docs list Google Gemini 3 family as a provider/integration. (verified 2026-10-29)
  • Hume EVI integrates with — Vapi docs list Hume EVI as a provider/integration. (verified 2026-10-29)
  • Inworld AI integrates with — Vapi docs list Inworld AI as a provider/integration. (verified 2026-10-29)
  • Langfuse integrates with — Vapi docs list Langfuse as a provider/integration. (verified 2026-10-29)
  • Mistral Large 2 / Mixtral family integrates with — Vapi docs list Mistral Large 2 / Mixtral family as a provider/integration. (verified 2026-10-29)
  • n8n (AI agent flows) integrates with — Vapi docs list n8n (AI agent flows) as a provider/integration. (verified 2026-10-29)
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with · depends on at runtime — adjacent-infrastructure cell: Twilio / Vonage SIP; Deepgram + Cartesia + Eleven STT/TTS; Anthropic / OpenAI LLMs
  • OpenRouter integrates with — Vapi docs list OpenRouter as a provider/integration. (verified 2026-10-29)
  • Speechmatics Flow integrates with — Vapi docs list Speechmatics Flow as a provider/integration. (verified 2026-10-29)
  • Together AI integrates with — Vapi docs list Together AI as a provider/integration. (verified 2026-10-29)
  • xAI Grok 4 integrates with — Vapi docs list xAI Grok 4 as a provider/integration. (verified 2026-10-29)

Referenced by (2)

  • Langfuse integrates with — Langfuse's integrations directory has a Vapi integration page. (verified 2026-10-29)
  • Retell AI competes with — Direct competitor to Vapi with proprietary-model focus.