Learn more">
Skip to navigation
/n <div>\n <img src=https://elevenlabs.io/"file:assets/images/agents/agents-overview-build.png/" alt=\"\" />\n </div>\n\n <div>\n <h3>\n Configure\n </h3>\n\n <p>\n Configure multimodal agents with our developer toolkit, dashboard, or visual workflow\n builder\n </p>\n </div>\n </a>\n\n <a href=https://elevenlabs.io/"/docs/eleven-agents/integrate/overview/">/n <div>\n <img src=https://elevenlabs.io/"file:assets/images/agents/agents-overview-integrate.png/" alt=\"\" />\n </div>\n\n <div>\n <h3>\n Deploy\n </h3>\n\n <p>\n Integrate multimodal agents across telephony systems, web, and mobile\n </p>\n </div>\n </a>\n\n <a href=https://elevenlabs.io/"/docs/eleven-agents/operate/overview/">/n <div>\n <img src=https://elevenlabs.io/"file:assets/images/agents/agents-overview-operate.png/" alt=\"\" />\n </div>\n\n <div>\n <h3>\n Monitor\n </h3>\n\n <p>\n Evaluate agent performance with built-in testing, evals, and analytics\n </p>\n </div>\n </a>\n</div>\n\n## Platform capabilities\n\nFrom design to deployment to optimization, ElevenLabs provides everything you need to build agents at scale.\n\n### Design and configure\n\n| Goal | Guide | Description |\n| ----------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------------------------------- |\n| Create conversation workflows | [Workflows](/docs/eleven-agents/customization/agent-workflows) | Build multi-step workflows with visual workflow builder |\n| Write system prompts | [System prompt](/docs/eleven-agents/best-practices/prompting-guide) | Learn best practices for crafting effective agent prompts |\n| Select language model | [Models](/docs/eleven-agents/customization/llm) | Choose from supported LLMs or bring your own custom model |\n| Control conversation flow | [Conversation flow](/docs/eleven-agents/customization/conversation-flow) | Configure turn-taking, interruptions, and timeout settings |\n| Configure voice & language | [Voice & language](/docs/eleven-agents/customization/voice) | Select from 10,000+ voices across 31 languages with customization options |\n| Add knowledge to agent | [Knowledge base](/docs/eleven-agents/customization/knowledge-base) | Upload documents and enable RAG for grounded responses |\n| Connect tools | [Tools](/docs/eleven-agents/customization/tools) | Enable agents to call clients & APIs to perform actions |\n| Personalize each conversation | [Personalization](/docs/eleven-agents/customization/personalization) | Use dynamic variables and overrides for per-conversation customization |\n| Secure agent access | [Authentication](/docs/eleven-agents/customization/authentication) | Implement custom authentication for protected agent access |\n\n### Connect and deploy\n\n| Goal | Guide | Description |\n| --------------------------- | --------------------------------------------------------------------------------- | ------------------------------------------------------------------ |\n| Build with React components | [ElevenLabs UI](https://ui.elevenlabs.io) | Pre-built components library for audio & agent apps (shadcn-based) |\n| Embed widget in website | [Widget](/docs/eleven-agents/customization/widget) | Add a customizable web widget to any website |\n| Build React web apps | [React SDK](/docs/eleven-agents/libraries/react) | Voice-enabled React hooks and components |\n| Build iOS apps | [Swift SDK](/docs/eleven-agents/libraries/swift) | Native iOS SDK for voice agents |\n| Build Android apps | [Kotlin SDK](/docs/eleven-agents/libraries/kotlin) | Native Android SDK for voice agents |\n| Build React Native apps | [React Native SDK](/docs/eleven-agents/libraries/react-native) | Cross-platform iOS and Android with React Native |\n| Connect via SIP trunk | [SIP trunk](/docs/eleven-agents/phone-numbers/sip-trunking) | Integrate with existing telephony infrastructure |\n| Make batch outbound calls | [Batch calls](/docs/eleven-agents/phone-numbers/batch-calls) | Trigger multiple calls programmatically |\n| Use Twilio integration | [Twilio](/docs/eleven-agents/phone-numbers/twilio-integration/native-integration) | Native Twilio integration for phone calls |\n| Build custom integrations | [WebSocket API](/docs/eleven-agents/libraries/web-sockets) | Low-level WebSocket protocol for custom implementations |\n| Receive real-time events | [Events](/docs/eleven-agents/customization/events) | Subscribe to conversation events and updates |\n\n### Monitor and optimize\n\n| Goal | Guide | Description |\n| ---------------------------- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------- |\n| List users by external ID | [Users](/docs/eleven-agents/operate/users) | See end users and open their conversations |\n| Search transcripts | [Searching conversations](/docs/eleven-agents/customization/agent-analysis/smart-search) | Keyword and semantic search in Conversation history |\n| Run A/B tests | [Experiments](/docs/eleven-agents/operate/experiments) | Test agent configuration changes with live traffic |\n| Test agent behavior | [Testing](/docs/eleven-agents/customization/agent-testing) | Create and run automated tests for your agents |\n| Analyze conversation quality | [Conversation analysis](/docs/eleven-agents/customization/agent-analysis) | Extract insights and evaluate conversation outcomes |\n| Track metrics & analytics | [Analytics](/docs/eleven-agents/dashboard) | Monitor performance metrics and conversation history |\n| Configure data retention | [Privacy](/docs/eleven-agents/customization/privacy) | Set retention policies for conversations and audio |\n| Reduce LLM costs | [Cost optimization](/docs/eleven-agents/customization/llm/optimizing-costs) | Monitor and optimize language model expenses |\n| Manage agents as code | [CLI](/docs/eleven-agents/operate/cli) | Version control and deploy agents from your terminal |\n| Manage agents from Claude | [Hosted MCP](/docs/eleven-agents/operate/hosted-mcp) | Create and update agents from any MCP client |\n\n## Architecture\n\nElevenAgents coordinates 4 core components:\n\n1. A fine-tuned Speech to Text (ASR) model for speech recognition\n2. Your choice of language model or [custom](/docs/eleven-agents/customization/llm/custom-llm) LLM\n3. A low-latency Text to Speech (TTS) model across 10,000+ voices and 70+ languages\n4. A proprietary turn-taking model that handles conversation timing\n\nVoice agents can also use a [Realtime model](/docs/eleven-agents/customization/realtime-models), an ElevenLabs model built for low-latency voice conversation.\n\n## How Eleven Realtime relates to ElevenAgents and Speech Engine\n\nElevenLabs offers three ways to add voice to a product, each suited to a different level of control and integration effort.\n\n| Product | What it is | Primary audience |\n| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **ElevenAgents** | A 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. |\n| **Realtime models** | A 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. |\n| **Speech Engine** | The 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. |\n\nSee the [OpenAI Realtime API compatibility guide](/docs/eleven-agents/guides/openai-realtime-compatibility) for connecting to Realtime models using OpenAI's Realtime SDK and wire protocol, and the [Speech Engine overview](/docs/overview/capabilities/speech-engine) for adding voice to an existing text agent.\n\n<Card title=\"Quickstart\" href=https://elevenlabs.io/"/docs/eleven-agents/quickstart/">/n Build your first agent in 5 minutes\n</Card>\n"],"perViewerCopy":[0,true],"askAiEnabled":[0,false],"skillsConfig":[0],"availability":[0],"pageActions":[0,{"options":[0,{"copyPage":[0,true],"viewAsMarkdown":[0,true],"askAi":[0,true],"openAi":[0,true],"claude":[0,true],"cursor":[0,true],"claudeCode":[0,true],"vscode":[0,false],"custom":[1,[[0,{"title":[0,"LLMs full"],"subtitle":[0,"See the entire documentation site as markdown for LLMs"],"url":[0,"https://elevenlabs.io/docs/llms-full.txt"],"icon":[0,"fa-solid fa-file-code"]}]]]}]}],"pageActionsStyle":[0,"default"],"pageActionFiles":[0],"showRssFeedButton":[0,false],"showPageActions":[0,true]}" ssr client="deferred" opts="{"name":"PageHeaderIsland","value":true}" await-children>
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.

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
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