Skip to navigation
Get started

ElevenAgents

Learn how to build, launch, and scale agents with ElevenLabs.

Agents accomplish tasks through natural dialogue - from quick requests to complex, open-ended workflows. ElevenLabs provides voice-rich, expressive models, developer tools for building multimodal agents, and tools to monitor and evaluate agent performance at scale.

Build your agent with your coding agent. No account or API key needed beforehand.

Paste this into Claude Code, Cursor or Codex. It signs you in or creates an account, creates a key, and asks what you’d like to build: describe the agent you want, and your coding agent creates it and adds it to your app.

Add ElevenLabs to my project: run `npx -y @elevenlabs/cli@latest onboard init` and follow what it prints.

See how it works, or read the onboard command’s source to see exactly what it tells your coding agent.

Platform capabilities

From design to deployment to optimization, ElevenLabs provides everything you need to build agents at scale.

Design and configure

GoalGuideDescription
Create conversation workflowsWorkflowsBuild multi-step workflows with visual workflow builder
Write system promptsSystem promptLearn best practices for crafting effective agent prompts
Select language modelModelsChoose from supported LLMs or bring your own custom model
Control conversation flowConversation flowConfigure turn-taking, interruptions, and timeout settings
Configure voice & languageVoice & languageSelect from 10,000+ voices across 31 languages with customization options
Add knowledge to agentKnowledge baseUpload documents and enable RAG for grounded responses
Connect toolsToolsEnable agents to call clients & APIs to perform actions
Personalize each conversationPersonalizationUse dynamic variables and overrides for per-conversation customization
Secure agent accessAuthenticationImplement custom authentication for protected agent access

Connect and deploy

GoalGuideDescription
Build with React componentsElevenLabs UIPre-built components library for audio & agent apps (shadcn-based)
Embed widget in websiteWidgetAdd a customizable web widget to any website
Build React web appsReact SDKVoice-enabled React hooks and components
Build iOS appsSwift SDKNative iOS SDK for voice agents
Build Android appsKotlin SDKNative Android SDK for voice agents
Build React Native appsReact Native SDKCross-platform iOS and Android with React Native
Build Unity gamesUnity SDKVoice agents in Unity scenes for desktop and WebGL builds
Connect via SIP trunkSIP trunkIntegrate with existing telephony infrastructure
Make batch outbound callsBatch callsTrigger multiple calls programmatically
Use Twilio integrationTwilioNative Twilio integration for phone calls
Build custom integrationsWebSocket APILow-level WebSocket protocol for custom implementations
Receive real-time eventsEventsSubscribe to conversation events and updates

Monitor and optimize

GoalGuideDescription
List users by external IDUsersSee end users and open their conversations
Search transcriptsSearching conversationsKeyword and semantic search in Conversation history
Run A/B testsExperimentsTest agent configuration changes with live traffic
Test agent behaviorTestingCreate and run automated tests for your agents
Analyze conversation qualityConversation analysisExtract insights and evaluate conversation outcomes
Track metrics & analyticsAnalyticsMonitor performance metrics and conversation history
Configure data retentionPrivacySet retention policies for conversations and audio
Reduce LLM costsCost optimizationMonitor and optimize language model expenses
Manage agents as codeCLIVersion control and deploy agents from your terminal
Manage agents from ClaudeHosted MCPCreate and update agents from any MCP client

Architecture

ElevenAgents coordinates 4 core components:

  1. A fine-tuned Speech to Text (ASR) model for speech recognition
  2. Your choice of language model or custom LLM
  3. A low-latency Text to Speech (TTS) model across 10,000+ voices and 70+ languages
  4. A proprietary turn-taking model that handles conversation timing

Voice agents can also use a Realtime model, an ElevenLabs model built for low-latency voice conversation.

How Eleven Realtime relates to ElevenAgents and Speech Engine

ElevenLabs offers three ways to add voice to a product, each suited to a different level of control and integration effort.

ProductWhat it isPrimary audience
ElevenAgentsA full omnichannel agents platform. Runs on Realtime models, or on a fully cascaded, configurable pipeline with custom TTS, LLM, STT, workflows, evals, and monitoring.Developers and enterprises building production agents at scale.
Realtime modelsA standalone API exposing a series of speech-to-speech models, each optimized for a different use case. Available directly through the Realtime API, or as a model option inside ElevenAgents.Developers and enterprises who want to add voice with minimal complexity, including teams already using another realtime voice API and looking to switch.
Speech EngineThe speech orchestration layer on its own, for teams that have already built a text-based chat agent and want to add voice.Developers and enterprises who have already built a text agent and want to add voice.

See the OpenAI Realtime API compatibility guide for connecting to Realtime models using OpenAI’s Realtime SDK and wire protocol, and the Speech Engine overview for adding voice to an existing text agent.

Quickstart

Build your first agent in 5 minutes