ElevenAgents vs Vapi (2026)

Integrations span helpdesk (Zendesk, Freshdesk, Intercom), CRM (Salesforce, HubSpot), ITSM (ServiceNow, Jira), calendar (Cal.com, Calendly, Google Calendar), storage, messaging (Slack, Telegram), search (Exa, Tavily) and CCaaS (Genesys, Five9), with client tools, webhook tools, code tools and MCP tools for anything else.

Sourceelevenlabs.io/docs/eleven-agents/overviewread 2026-09-05

Function tools call the customer's server logic, and API Request tools call any HTTPS API directly with credentials held by reference. MCP tools connect an assistant to external MCP servers at runtime. Built in tools transfer calls, end calls, send SMS and press DTMF keys, and prebuilt integrations include Google Calendar event creation, Make and n8n. Deepgram, OpenAI and other providers are model layers, not integrations.

SourceVapi, docs.vapi.ai (Function tools, Integrations, Built-in tools)read 2026-09-27

Multi-step conversation workflows are built in a visual workflow builder, with free-form and structured Procedures carrying their own create, compile and draft endpoints, agent transfer between agents, and agent branches that support merge and rebase before deployment.

Sourceelevenlabs.io/docs/eleven-agents/customization/agent-workflowsread 2026-09-05

Squads split a call across specialized assistants that hand off to each other through handoff tools with declared destinations, resolved at runtime. Context passing, variable extraction and rejection rules are all configurable, and the squad examples route callers by verification and inquiry type. Vapi's older Workflows builder has been retired and its flows moved to Squads.

SourceVapi, docs.vapi.ai (Introduction to Squads, Handoff tool, Workflows migration guide)read 2026-09-27

Agents run on inbound and outbound telephony over SIP trunking, Twilio, Vonage, Telnyx, Plivo, Exotel and Bandwidth, CCaaS via Genesys and Five9, Microsoft Teams, WhatsApp with outbound templates, SMS, a web widget, mobile SDKs, programmatic batch calling and a real-time event subscription API.

Sourceelevenlabs.io/docs/eleven-agents/integrate/overviewread 2026-09-05

Outbound campaigns carry a schedulePlan with an earliest and latest dispatch time, so Vapi starts dialing a contact list on its own schedule, with pre dial webhooks. Assistant hooks run actions on call events. Agents also answer on Vapi, Twilio, Telnyx and SIP numbers, in web calls and over SMS chat.

SourceVapi, docs.vapi.ai (Campaign scheduling and lifecycle, Assistant hooks, SIP introduction, SMS chat)read 2026-09-27

The platform builds and holds the knowledge base, with documents ingested from file, text or URL, website crawl jobs, folders, document refresh, and RAG indexes with their own compute, batch compute, retrieve and delete endpoints plus chunk level inspection and semantic search. The knowledge base persists between conversations.

Sourceelevenlabs.io/docs/eleven-agents/customization/knowledge-base/ragread 2026-09-05

Knowledge bases are the customer's uploaded files, such as txt, pdf, docx, csv, md and more, added through the dashboard or the file API, kept in Vapi and attached to assistants. During a call the query tool searches them by file ID, with Google Gemini models doing the retrieval, and new knowledge is added by uploading a file instead of retraining. A custom knowledge base can swap in the customer's own retrieval server.

SourceVapi, docs.vapi.ai (Knowledge bases, Query tool)read 2026-09-27

Within a conversation, the update-state system tool holds state, with dynamic variables and overrides injected per conversation by the customer. Beyond the session, conversation history is kept against an external user id under the retention policy, and ElevenLabs does not describe a memory the agent recalls from across sessions.

Sourceelevenlabs.io/docs/eleven-agents/customization/personalizationread 2026-09-05

For chat and SMS, a sessionId groups chats under one persisted conversation that expires 24 hours after creation by default (expirationSeconds). Sessions can be read in session logs and deleted through the API, and within a call, squads carry context across handoffs. Nothing the agent learns about a caller is kept beyond the session.

SourceVapi, docs.vapi.ai (Session management, Session logs)read 2026-09-27

MCP servers carry an approval policy with endpoints to set the policy and to create or delete approvals for each tool, so the customer decides which actions the agent may take unattended and which are held for sign off, alongside guardrails that block out of scope requests before a response is sent and transfer tools for handing to a person.

Sourceelevenlabs.io/docs/eleven-agents/best-practices/guardrailsread 2026-09-05

A tool rejection plan attaches conditions to any tool and blocks the call when the recent conversation state matches them, and handoff rejection rules block unwanted transfers between assistants. Transfer tools hand a caller to a person by blind or warm transfer. There is no approval step that holds an action until a person signs off, so escalation hands over the whole conversation.

SourceVapi, docs.vapi.ai (Tool rejection plan, Transfer Call tool)read 2026-09-27

ElevenLabs publishes SOC 2 Type II, ISO 27001, ISO 42001, PCI DSS Level 1, HIPAA with a Business Associate Agreement, AIUC-1, GDPR and TXRAMP Level 2 through a live trust center, alongside customer-facing controls including SSO, granular workspace access permissions, a workspace secrets store, configurable retention, conversation history redaction and Zero Retention Mode.

Sourcecompliance.elevenlabs.ioread 2026-09-05

Vapi supports SSO through any SAML 2.0 or OIDC identity provider on the Enterprise and Premier plans, and RBAC with Admin, Editor and Viewer roles assigned per member. SCIM is not supported. Vapi's SafeBase trust center announces a completed SOC 2 Type II examination, with the report under NDA, and a public SOC 3, and lists HIPAA, PCI DSS v4.0.1, GDPR and CCPA. HIPAA mode and zero data retention are organization settings.

SourceVapi, docs.vapi.ai (Single Sign-On) and security.vapi.airead 2026-09-27

OpenTelemetry traces export the agent's execution to the customer's own observability stack, with real-time monitoring, a tool-executions endpoint, conversation analysis with success evaluation and sentiment, keyword and semantic transcript search, and per-conversation audio and detail retrieval.

Sourceelevenlabs.io/docs/eleven-agents/customization/opentelemetry-tracesread 2026-09-05

Call logs hold the transcript, messages, analysis, costs, latency, recordings and downloadable pipeline logs for each call, with chat, session, webhook and API request logs beside them. Monitors evaluate call data against thresholds and open issues. Raw data is kept for 14 to 180 days depending on the package.

SourceVapi, docs.vapi.ai (Call logs, Logs overview, Monitoring quickstart) and vapi.ai/pricingread 2026-09-27

Data residency is offered through isolated environments the customer selects, with storage locations in the United States, the European Union, India and Singapore, alongside VPC and on-premises options. Those isolated environments come only with the Enterprise plan.

Sourceelevenlabs.io/docs/overview/administration/data-residencyread 2026-09-05

Each organization belongs to the United States or the European Union region, with its own dashboard, API and SIP hosts, such as api.eu.vapi.ai and sip.eu.vapi.ai in the EU. Every resource stays in its region, and each region is an isolated environment. The service is hosted only, with no self hosted or customer tenant option.

SourceVapi, docs.vapi.ai (EU region and data residency)read 2026-09-27

ElevenAgents offers a workflow template library plus named role-specific agents the customer clones as units, including Order Support, Triage Agent, Front Desk Agent and FAQ Agent, and use-case starters for appointment scheduling, invoice management, purchase assistance and account support, all browsable and selectable from the app.

Sourceelevenlabs.io/agent-templatesread 2026-09-05

Cloneable example builds cover appointment scheduling, medical triage and scheduling, ecommerce order management, property management routing, lead qualification and multilingual support. Each does a different job, but the customer builds each one step by step instead of adopting a packaged agent. Model Intelligence presets are settings.

SourceVapi, docs.vapi.ai (Guides)read 2026-09-27

The customer selects the language model that powers the agent from a supported list, or brings their own through documented custom LLM integrations with Cloudflare, Groq, SambaNova and Together AI, with LLM cascading for fallback and a list-LLMs endpoint. The platform is explicitly model-agnostic and supplies only the speech and turn-taking models itself.

Sourceelevenlabs.io/docs/eleven-agents/customization/llmread 2026-09-05

Each assistant's transcriber, model and voice can be swapped for any supported provider. Customers can use their own provider keys, Azure OpenAI and Bedrock credentials, or their own server acting as the LLM. Transcriber and voice fallback plans switch providers automatically on failure.

SourceVapi, docs.vapi.ai (Core Models, Provider Keys, Custom LLM, fallback configuration)read 2026-09-27

ElevenAgents offers a full REST and WebSocket API for the platform itself covering agents, conversations, tools, knowledge base, tests, phone numbers and workspace settings, native SDKs for Python, JavaScript, React, React Native, Swift and Kotlin, post-call webhooks, a CLI for managing agents as code, and a hosted MCP server that lets an external assistant create and update agents.

Sourceelevenlabs.io/docs/eleven-agents/api-reference/introductionread 2026-09-05

The API covers assistants, squads, calls, chats, campaigns, sessions and phone numbers, with server SDKs, a Web SDK and a CLI beside it. The Vapi MCP Server at mcp.vapi.ai, authenticated by bearer token, manages assistants, phone numbers and calls from any MCP client.

SourceVapi, docs.vapi.ai (API reference, Vapi MCP Server)read 2026-09-27

ElevenAgents ships a customer-facing test suite: automated tests with folders, invocations and a run-tests endpoint, conversation simulation including a streaming variant, Experiments for A/B testing configuration changes against live traffic, agent versioning, and a run-evaluation endpoint returning success criteria per conversation, all run against the customer's own agent.

Sourceelevenlabs.io/docs/eleven-agents/customization/agent-testingread 2026-09-05

Evals test assistants and squads with mock conversations, using exact, regex or AI judged checks and tool call checks, and return pass or fail. Simulations run full conversations against AI testers with success criteria and tool mocks, and the testing guides set a release and regression cadence.

SourceVapi, docs.vapi.ai (Evals quickstart, Simulations overview, Run and maintain tests)read 2026-09-27

The agent acts only through programmatic surfaces, client tools, webhook tools, code tools, MCP servers and system tools for call control. ElevenLabs does not describe browser control, a virtual desktop or operating software that has no programmatic interface.

Sourceelevenlabs.io/docs/eleven-agents/customization/toolsread 2026-09-05

Browser, desktop and computer control are not described. IVR navigation presses DTMF keys to walk a phone menu on a telephone keypad, not a screen. Web SDK client side tools trigger side effects in the customer's own web app, which is the product running in a browser.

SourceVapi, docs.vapi.ai (llms.txt, IVR Navigation, Client-side tools)read 2026-09-27