Documentation
Build with Kilevel
Everything needed to take a voice agent from an empty workspace to answering calls in production — and the public API underneath it.
Quickstart
Place your first call from the API in four steps.
API reference
Every endpoint, with a built-in playground.
Integrations
Calendars, CRMs, telephony, models and MCP.
Sections
GuidesBuild, launch and improve voice and chat agents.IntegrationsConnect calendars, workspace tools, providers and telephony.DevelopersAuthenticate, call the API, receive webhooks, use MCP.API referenceEvery public endpoint, generated from the live service.AdministrationTeam, API keys, billing, limits, agencies and compliance.ChangelogWhat is new in Kilevel, newest first.
Getting started
- What is KilevelA voice AI platform for building agents that answer and place real phone calls, run the conversation against your own data, and hand off to the rest of your stack.
- QuickstartPlace your first outbound call from the API in four steps — key, flow, call, result.
- Core conceptsFlows, agents, call jobs, applications, data stores and phone numbers — what each object is and which one you actually want.
Build
- Flows and agentsThe flow holds what a conversation does; the agent decides how it sounds. How the two fit together, and how a flow is structured.
- Voice and languageSpeech recognition, voices, languages and pronunciation — and how the assistant handles interruptions and silence.
- Knowledge baseGive an agent documents, web pages and text to answer from — shared across agents or kept local to one.
- ToolsLet the assistant act during a conversation — built-in tools, your own HTTP endpoints, call transfers and long-running asynchronous work.
- Call transfersHand a call to a phone number, a SIP destination or another flow — blind, or warm with a briefing for the person picking up.
- Structured outputsTurn every conversation into fields your systems can use — defined once as a schema, filled after each call or chat.
Launch
- Phone numbersConnect numbers through Twilio, Telnyx or your own SIP trunk, decide what each is for, and set how many calls it may carry at once.
- Inbound callsDecide what happens when a number rings — the agent answers, the call rings through, is rejected, forwarded, or handed to your own system.
- CampaignsWork through a list of contacts with call jobs — call windows, pacing, retries and results, from the dashboard or the API.
- Website widgetPut your agent on your website — chat, or a voice call straight from the browser — with one script tag.
- Messaging channelsRun the same flows over WhatsApp, SMS, email and Slack — and start conversations yourself from the API.
Monitor & improve
- Call and chat historyEvery conversation leaves a record — transcript, recording, outcome and extracted fields — to review, export or pull over the API.
- Live monitoringListen to calls as they happen, follow live captions, and step in — by injecting speech, or by taking the call yourself.
- TranscriptionTranscribe audio recorded outside Kilevel — uploads, cloud storage, FTP, Google Drive or URLs — and run the same analysis a call gets.
- PerformanceHow every agent is doing, across calls, chats and imported recordings — scorecards, trends, alerts, calibration, and the privacy settings a works council agreement needs.
- Evaluations and benchmarksTest a flow against scenarios before it meets real callers, and compare models and settings with benchmarks.
- AutomationsWorkflows that run around your conversations — triggered by calls, schedules or webhooks, and connected to the rest of your stack.