Get started

Agents Platform

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 5k+ 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
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

Architecture

The Agents Platform 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 5k+ voices and 31 languages
  4. A proprietary turn-taking model that handles conversation timing
Quickstart

Build your first agent in 5 minutes