elevenlabs-agents
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseElevenLabs Agents Platform
ElevenLabs Agents平台
Overview
概述
ElevenLabs Agents Platform is a comprehensive solution for building production-ready conversational AI voice agents. The platform coordinates four core components:
- ASR (Automatic Speech Recognition) - Converts speech to text (32+ languages, sub-second latency)
- LLM (Large Language Model) - Reasoning and response generation (GPT, Claude, Gemini, custom models)
- TTS (Text-to-Speech) - Converts text to speech (5000+ voices, 31 languages, low latency)
- Turn-Taking Model - Proprietary model that handles conversation timing and interruptions
ElevenLabs Agents平台是构建生产级对话式AI语音代理的综合性解决方案。该平台协调四大核心组件:
- ASR(自动语音识别) - 将语音转换为文本(支持32+种语言,亚秒级延迟)
- LLM(大语言模型) - 推理与响应生成(支持GPT、Claude、Gemini及自定义模型)
- TTS(文本转语音) - 将文本转换为语音(5000+种语音,覆盖31种语言,低延迟)
- 轮次对话模型 - 专有模型,处理对话时序与打断逻辑
🚨 Package Updates (November 2025)
🚨 包更新(2025年11月)
ElevenLabs migrated to new scoped packages in August 2025:
DEPRECATED (Do not use):
- → DEPRECATED
@11labs/react - → DEPRECATED
@11labs/client
Current packages:
bash
npm install @elevenlabs/react@0.9.1 # React SDK
npm install @elevenlabs/client@0.9.1 # JavaScript SDK
npm install @elevenlabs/react-native@0.5.2 # React Native SDK
npm install @elevenlabs/elevenlabs-js@2.21.0 # Base SDK
npm install -g @elevenlabs/agents-cli@0.2.0 # CLIIf you have old packages installed, uninstall them first:
bash
npm uninstall @11labs/react @11labs/clientElevenLabs于2025年8月迁移至新的作用域包:
已弃用(请勿使用):
- → 已弃用
@11labs/react - → 已弃用
@11labs/client
当前可用包:
bash
npm install @elevenlabs/react@0.9.1 # React SDK
npm install @elevenlabs/client@0.9.1 # JavaScript SDK
npm install @elevenlabs/react-native@0.5.2 # React Native SDK
npm install @elevenlabs/elevenlabs-js@2.21.0 # 基础SDK
npm install -g @elevenlabs/agents-cli@0.2.0 # CLI工具若已安装旧包,请先卸载:
bash
npm uninstall @11labs/react @11labs/clientWhen to Use This Skill
适用场景
Use this skill when:
- Building voice-enabled customer support agents
- Creating interactive voice response (IVR) systems
- Developing conversational AI applications
- Integrating telephony (Twilio, SIP trunking)
- Implementing voice chat in web/mobile apps
- Configuring agents via CLI ("agents as code")
- Setting up RAG/knowledge bases for agents
- Integrating MCP (Model Context Protocol) servers
- Building HIPAA/GDPR-compliant voice systems
- Optimizing LLM costs with caching strategies
在以下场景中使用本技能:
- 构建语音客服代理
- 创建交互式语音应答(IVR)系统
- 开发对话式AI应用
- 集成电话系统(Twilio、SIP中继)
- 在Web/移动应用中实现语音聊天
- 通过CLI以“代理即代码”方式配置代理
- 为代理设置RAG/知识库
- 集成MCP(模型上下文协议)服务器
- 构建符合HIPAA/GDPR规范的语音系统
- 通过缓存策略优化LLM成本
Platform Capabilities
平台能力
Design & Configure:
- Multi-step workflows with visual builder
- System prompt engineering (6-component framework)
- 5000+ voices across 31 languages
- Pronunciation dictionaries (IPA/CMU formats)
- Speed control (0.7x-1.2x)
- RAG-powered knowledge bases
- Dynamic variables and personalization
Connect & Deploy:
- React SDK ()
@elevenlabs/react - JavaScript SDK ()
@elevenlabs/client - React Native SDK ()
@elevenlabs/react-native - Swift SDK (iOS/macOS)
- Embeddable widget
- Telephony integration (Twilio, SIP)
- Scribe (Real-Time Speech-to-Text) - Beta
Operate & Optimize:
- Automated testing (scenario, tool call, load)
- Conversation analysis and evaluation
- Analytics dashboard (resolution rates, sentiment, compliance)
- Privacy controls (GDPR, HIPAA, SOC 2)
- Cost optimization (LLM caching, model swapping, burst pricing)
- CLI for "agents as code" workflow
设计与配置:
- 可视化构建器创建多步骤工作流
- 系统提示词工程(6组件框架)
- 覆盖31种语言的5000+种语音
- 发音词典(IPA/CMU格式)
- 语速控制(0.7x-1.2x)
- RAG驱动的知识库
- 动态变量与个性化设置
连接与部署:
- React SDK ()
@elevenlabs/react - JavaScript SDK ()
@elevenlabs/client - React Native SDK ()
@elevenlabs/react-native - Swift SDK(iOS/macOS)
- 可嵌入组件
- 电话系统集成(Twilio、SIP)
- Scribe(实时语音转文本)- 测试版
运营与优化:
- 自动化测试(场景测试、工具调用测试、负载测试)
- 对话分析与评估
- 分析仪表盘(解决率、情感分析、合规性)
- 隐私控制(GDPR、HIPAA、SOC 2)
- 成本优化(LLM缓存、模型切换、峰值定价)
- 用于“代理即代码”工作流的CLI工具
1. Quick Start (3 Integration Paths)
1. 快速开始(3种集成路径)
Path A: React SDK (Embedded Voice Chat)
路径A:React SDK(嵌入式语音聊天)
For building voice chat interfaces in React applications.
Installation:
bash
npm install @elevenlabs/react zodBasic Example:
typescript
import { useConversation } from '@elevenlabs/react';
import { z } from 'zod';
export default function VoiceChat() {
const { startConversation, stopConversation, status } = useConversation({
// Public agent (no API key needed)
agentId: 'your-agent-id',
// OR private agent (requires API key)
apiKey: process.env.NEXT_PUBLIC_ELEVENLABS_API_KEY,
// OR signed URL (server-generated, most secure)
signedUrl: '/api/elevenlabs/auth',
// Client-side tools (browser functions)
clientTools: {
updateCart: {
description: "Update the shopping cart",
parameters: z.object({
item: z.string(),
quantity: z.number()
}),
handler: async ({ item, quantity }) => {
console.log('Updating cart:', item, quantity);
return { success: true };
}
}
},
// Event handlers
onConnect: () => console.log('Connected'),
onDisconnect: () => console.log('Disconnected'),
onEvent: (event) => {
switch (event.type) {
case 'transcript':
console.log('User said:', event.data.text);
break;
case 'agent_response':
console.log('Agent replied:', event.data.text);
break;
}
},
// Regional compliance (GDPR, data residency)
serverLocation: 'us' // 'us' | 'global' | 'eu-residency' | 'in-residency'
});
return (
<div>
<button onClick={startConversation}>Start Conversation</button>
<button onClick={stopConversation}>Stop</button>
<p>Status: {status}</p>
</div>
);
}适用于在React应用中构建语音聊天界面。
安装:
bash
npm install @elevenlabs/react zod基础示例:
typescript
import { useConversation } from '@elevenlabs/react';
import { z } from 'zod';
export default function VoiceChat() {
const { startConversation, stopConversation, status } = useConversation({
// 公共代理(无需API密钥)
agentId: 'your-agent-id',
// 或私有代理(需要API密钥)
apiKey: process.env.NEXT_PUBLIC_ELEVENLABS_API_KEY,
// 或签名URL(服务器生成,最安全)
signedUrl: '/api/elevenlabs/auth',
// 客户端工具(浏览器端函数)
clientTools: {
updateCart: {
description: "Update the shopping cart",
parameters: z.object({
item: z.string(),
quantity: z.number()
}),
handler: async ({ item, quantity }) => {
console.log('Updating cart:', item, quantity);
return { success: true };
}
}
},
// 事件处理器
onConnect: () => console.log('Connected'),
onDisconnect: () => console.log('Disconnected'),
onEvent: (event) => {
switch (event.type) {
case 'transcript':
console.log('User said:', event.data.text);
break;
case 'agent_response':
console.log('Agent replied:', event.data.text);
break;
}
},
// 区域合规(GDPR、数据驻留)
serverLocation: 'us' // 'us' | 'global' | 'eu-residency' | 'in-residency'
});
return (
<div>
<button onClick={startConversation}>Start Conversation</button>
<button onClick={stopConversation}>Stop</button>
<p>Status: {status}</p>
</div>
);
}Path B: CLI ("Agents as Code")
路径B:CLI(“代理即代码”)
For managing agents via code with version control and CI/CD.
Installation:
bash
npm install -g @elevenlabs/agents-cli适用于通过代码管理代理,支持版本控制与CI/CD。
安装:
bash
npm install -g @elevenlabs/agents-clior
或
pnpm install -g @elevenlabs/agents-cli
**Workflow**:
```bashpnpm install -g @elevenlabs/agents-cli
**工作流**:
```bash1. Authenticate
1. 认证
elevenlabs auth login
elevenlabs auth login
2. Initialize project (creates agents.json, tools.json, tests.json)
2. 初始化项目(创建agents.json、tools.json、tests.json)
elevenlabs agents init
elevenlabs agents init
3. Create agent from template
3. 从模板创建代理
elevenlabs agents add "Support Agent" --template customer-service
elevenlabs agents add "Support Agent" --template customer-service
4. Configure in agent_configs/support-agent.json
4. 在agent_configs/support-agent.json中配置
5. Push to platform
5. 推送到平台
elevenlabs agents push --env dev
elevenlabs agents push --env dev
6. Test
6. 测试
elevenlabs agents test "Support Agent"
elevenlabs agents test "Support Agent"
7. Deploy to production
7. 部署到生产环境
elevenlabs agents push --env prod
**Project Structure Created**:your_project/
├── agents.json # Agent registry
├── tools.json # Tool configurations
├── tests.json # Test configurations
├── agent_configs/ # Individual agent files
├── tool_configs/ # Tool configuration files
└── test_configs/ # Test configuration files
undefinedelevenlabs agents push --env prod
**生成的项目结构**:your_project/
├── agents.json # 代理注册表
├── tools.json # 工具配置
├── tests.json # 测试配置
├── agent_configs/ # 单个代理文件
├── tool_configs/ # 工具配置文件
└── test_configs/ # 测试配置文件
undefinedPath C: API (Programmatic Agent Management)
路径C:API(程序化代理管理)
For creating agents dynamically (multi-tenant, SaaS platforms).
Installation:
bash
npm install elevenlabsExample:
typescript
import { ElevenLabsClient } from 'elevenlabs';
const client = new ElevenLabsClient({
apiKey: process.env.ELEVENLABS_API_KEY
});
// Create agent
const agent = await client.agents.create({
name: 'Support Bot',
conversation_config: {
agent: {
prompt: {
prompt: "You are a helpful customer support agent.",
llm: "gpt-4o",
temperature: 0.7
},
first_message: "Hello! How can I help you today?",
language: "en"
},
tts: {
model_id: "eleven_turbo_v2_5",
voice_id: "your-voice-id"
}
}
});
console.log('Agent created:', agent.agent_id);适用于动态创建代理(多租户、SaaS平台)。
安装:
bash
npm install elevenlabs示例:
typescript
import { ElevenLabsClient } from 'elevenlabs';
const client = new ElevenLabsClient({
apiKey: process.env.ELEVENLABS_API_KEY
});
// 创建代理
const agent = await client.agents.create({
name: 'Support Bot',
conversation_config: {
agent: {
prompt: {
prompt: "You are a helpful customer support agent.",
llm: "gpt-4o",
temperature: 0.7
},
first_message: "Hello! How can I help you today?",
language: "en"
},
tts: {
model_id: "eleven_turbo_v2_5",
voice_id: "your-voice-id"
}
}
});
console.log('Agent created:', agent.agent_id);2. Agent Configuration
2. 代理配置
System Prompt Architecture (6 Components)
系统提示词架构(6组件)
ElevenLabs recommends structuring agent prompts using 6 components:
ElevenLabs推荐使用6组件结构构建代理提示词:
1. Personality
1. 人格
Define the agent's identity, role, and character traits.
Example:
You are Alex, a friendly and knowledgeable customer support specialist at TechCorp.
You have 5 years of experience helping customers solve technical issues.
You're patient, empathetic, and always maintain a positive attitude.定义代理的身份、角色与性格特征。
示例:
You are Alex, a friendly and knowledgeable customer support specialist at TechCorp.
You have 5 years of experience helping customers solve technical issues.
You're patient, empathetic, and always maintain a positive attitude.2. Environment
2. 环境
Describe the communication context (phone, web chat, video call).
Example:
You're speaking with customers over the phone. Communication is voice-only.
Customers may have background noise or poor connection quality.
Speak clearly and occasionally use thoughtful pauses for emphasis.描述沟通场景(电话、网页聊天、视频通话)。
示例:
You're speaking with customers over the phone. Communication is voice-only.
Customers may have background noise or poor connection quality.
Speak clearly and occasionally use thoughtful pauses for emphasis.3. Tone
3. 语气
Specify formality, speech patterns, humor, and verbosity.
Example:
Tone: Professional yet warm. Use contractions ("I'm" instead of "I am") to sound natural.
Avoid jargon unless the customer uses it first. Keep responses concise (2-3 sentences max).
Use encouraging phrases like "I'll be happy to help with that" and "Let's get this sorted for you."指定正式程度、说话风格、幽默感与 verbose 程度。
示例:
Tone: Professional yet warm. Use contractions ("I'm" instead of "I am") to sound natural.
Avoid jargon unless the customer uses it first. Keep responses concise (2-3 sentences max).
Use encouraging phrases like "I'll be happy to help with that" and "Let's get this sorted for you."4. Goal
4. 目标
Define objectives and success criteria.
Example:
Primary Goal: Resolve customer technical issues on the first call.
Secondary Goals:
- Verify customer identity securely
- Document issue details accurately
- Offer proactive solutions
- End calls with confirmation that the issue is resolved
Success Criteria: Customer verbally confirms their issue is resolved.定义目标与成功标准。
示例:
Primary Goal: Resolve customer technical issues on the first call.
Secondary Goals:
- Verify customer identity securely
- Document issue details accurately
- Offer proactive solutions
- End calls with confirmation that the issue is resolved
Success Criteria: Customer verbally confirms their issue is resolved.5. Guardrails
5. 防护规则
Set boundaries, prohibited topics, and ethical constraints.
Example:
Guardrails:
- Never provide medical, legal, or financial advice
- Do not share confidential company information
- If asked about competitors, politely redirect to TechCorp's offerings
- Escalate to a human supervisor if customer becomes abusive
- Never make promises about refunds or credits without verification设置边界、禁止话题与伦理约束。
示例:
Guardrails:
- Never provide medical, legal, or financial advice
- Do not share confidential company information
- If asked about competitors, politely redirect to TechCorp's offerings
- Escalate to a human supervisor if customer becomes abusive
- Never make promises about refunds or credits without verification6. Tools
6. 工具
Describe available external capabilities and when to use them.
Example:
Available Tools:
1. lookup_order(order_id) - Fetch order details from database. Use when customer mentions an order number.
2. transfer_to_supervisor() - Escalate to human agent. Use when issue requires manager approval.
3. send_password_reset(email) - Trigger password reset email. Use when customer can't access account.
Always explain to the customer what you're doing before calling a tool.Complete Template:
json
{
"agent": {
"prompt": {
"prompt": "Personality:\nYou are Alex, a friendly customer support specialist.\n\nEnvironment:\nYou're speaking with customers over the phone.\n\nTone:\nProfessional yet warm. Keep responses concise.\n\nGoal:\nResolve technical issues on the first call.\n\nGuardrails:\n- Never provide medical/legal/financial advice\n- Escalate abusive customers\n\nTools:\n- lookup_order(order_id) - Fetch order details\n- transfer_to_supervisor() - Escalate to human",
"llm": "gpt-4o",
"temperature": 0.7,
"max_tokens": 500
}
}
}描述可用的外部能力及使用场景。
示例:
Available Tools:
1. lookup_order(order_id) - Fetch order details from database. Use when customer mentions an order number.
2. transfer_to_supervisor() - Escalate to human agent. Use when issue requires manager approval.
3. send_password_reset(email) - Trigger password reset email. Use when customer can't access account.
Always explain to the customer what you're doing before calling a tool.完整模板:
json
{
"agent": {
"prompt": {
"prompt": "Personality:\nYou are Alex, a friendly customer support specialist.\n\nEnvironment:\nYou're speaking with customers over the phone.\n\nTone:\nProfessional yet warm. Keep responses concise.\n\nGoal:\nResolve technical issues on the first call.\n\nGuardrails:\n- Never provide medical/legal/financial advice\n- Escalate abusive customers\n\nTools:\n- lookup_order(order_id) - Fetch order details\n- transfer_to_supervisor() - Escalate to human",
"llm": "gpt-4o",
"temperature": 0.7,
"max_tokens": 500
}
}
}Turn-Taking Modes
轮次对话模式
Controls when the agent interrupts or waits for the user to finish speaking.
3 Modes:
| Mode | Behavior | Best For |
|---|---|---|
| Eager | Responds quickly, jumps in at earliest opportunity | Fast-paced support, quick orders |
| Normal | Balanced, waits for natural conversation breaks | General customer service (default) |
| Patient | Waits longer, allows detailed user responses | Information collection, therapy, tutoring |
Configuration:
json
{
"conversation_config": {
"turn": {
"mode": "patient" // "eager" | "normal" | "patient"
}
}
}Use Cases:
- Eager: Fast food ordering, quick FAQs, urgent notifications
- Normal: General support, product inquiries, appointment booking
- Patient: Detailed form filling, emotional support, educational tutoring
Gotchas:
- Eager mode can feel interruptive to some users
- Patient mode may feel slow in fast-paced contexts
- Can be dynamically adjusted in workflows for context-aware behavior
控制代理何时打断用户或等待用户说完。
3种模式:
| 模式 | 行为 | 适用场景 |
|---|---|---|
| Eager(积极) | 快速响应,尽早插入对话 | 快节奏客服、快速下单 |
| Normal(正常) | 平衡模式,等待自然对话停顿 | 通用客服(默认) |
| Patient(耐心) | 等待更长时间,允许用户详细表达 | 信息收集、心理咨询、辅导 |
配置:
json
{
"conversation_config": {
"turn": {
"mode": "patient" // "eager" | "normal" | "patient"
}
}
}适用场景:
- Eager:快餐点餐、快速FAQ、紧急通知
- Normal:通用客服、产品咨询、预约预订
- Patient:详细表单填写、情感支持、教育辅导
注意事项:
- Eager模式可能对部分用户造成打断感
- Patient模式在快节奏场景中可能显得缓慢
- 可在工作流中动态调整,实现上下文感知的对话行为
Workflows (Visual Builder)
工作流(可视化构建器)
Create branching conversation flows with subagent nodes and conditional routing.
Node Types:
- Subagent Nodes - Override base agent config (change prompt, voice, turn-taking)
- Tool Nodes - Guarantee tool execution (unlike tools in subagents)
Configuration:
json
{
"workflow": {
"nodes": [
{
"id": "node_1",
"type": "subagent",
"config": {
"system_prompt": "You are now a technical support specialist. Ask detailed diagnostic questions.",
"turn_eagerness": "patient",
"voice_id": "tech_support_voice_id"
}
},
{
"id": "node_2",
"type": "tool",
"tool_name": "transfer_to_human"
}
],
"edges": [
{
"from": "node_1",
"to": "node_2",
"condition": "user_requests_escalation"
}
]
}
}Use Cases:
- Multi-department routing (sales → support → billing)
- Decision trees ("press 1 for sales, 2 for support")
- Role-playing scenarios (customer vs agent voices)
- Escalation paths (bot → human transfer)
Gotchas:
- Workflows add ~100-200ms latency per node transition
- Tool nodes guarantee execution (subagents may skip tools)
- Edges can create infinite loops if not tested properly
创建包含子代理节点与条件路由的分支对话流。
节点类型:
- 子代理节点 - 覆盖基础代理配置(修改提示词、语音、轮次对话模式)
- 工具节点 - 确保工具执行(与子代理中的工具不同,子代理可能跳过工具)
配置:
json
{
"workflow": {
"nodes": [
{
"id": "node_1",
"type": "subagent",
"config": {
"system_prompt": "You are now a technical support specialist. Ask detailed diagnostic questions.",
"turn_eagerness": "patient",
"voice_id": "tech_support_voice_id"
}
},
{
"id": "node_2",
"type": "tool",
"tool_name": "transfer_to_human"
}
],
"edges": [
{
"from": "node_1",
"to": "node_2",
"condition": "user_requests_escalation"
}
]
}
}适用场景:
- 多部门路由(销售→客服→计费)
- 决策树(“按1转销售,按2转客服”)
- 角色扮演场景(客户与代理语音切换)
- 升级路径(机器人→人工转接)
注意事项:
- 工作流每个节点转换会增加约100-200ms延迟
- 工具节点确保执行(子代理可能跳过工具)
- 若未测试,边配置可能导致无限循环
Dynamic Variables & Personalization
动态变量与个性化
Inject runtime data into prompts, first messages, and tool parameters using syntax.
{{var_name}}System Variables (Auto-Available):
typescript
{{system__agent_id}} // Current agent ID
{{system__conversation_id}} // Conversation ID
{{system__caller_id}} // Phone number (telephony only)
{{system__called_number}} // Called number (telephony only)
{{system__call_duration_secs}} // Call duration
{{system__time_utc}} // Current UTC time
{{system__call_sid}} // Twilio call SID (Twilio only)Custom Variables:
typescript
// Provide when starting conversation
const conversation = await client.conversations.create({
agent_id: "agent_123",
dynamic_variables: {
user_name: "John",
account_tier: "premium",
order_id: "ORD-12345"
}
});Secret Variables (For API Keys):
{{secret__stripe_api_key}}
{{secret__database_password}}Important: Secret variables only used in headers, never sent to LLM providers.
Usage in Prompts:
json
{
"agent": {
"prompt": {
"prompt": "You are helping {{user_name}}, a {{account_tier}} customer."
},
"first_message": "Hello {{user_name}}! I see you're calling about order {{order_id}}."
}
}Gotcha: Missing variables cause "Missing required dynamic variables" error. Always provide all referenced variables when starting conversation.
使用语法在提示词、初始消息与工具参数中注入运行时数据。
{{var_name}}系统变量(自动可用):
typescript
{{system__agent_id}} // 当前代理ID
{{system__conversation_id}} // 对话ID
{{system__caller_id}} // 电话号码(仅电话系统)
{{system__called_number}} // 被叫号码(仅电话系统)
{{system__call_duration_secs}} // 通话时长
{{system__time_utc}} // 当前UTC时间
{{system__call_sid}} // Twilio通话SID(仅Twilio)自定义变量:
typescript
// 启动对话时提供
const conversation = await client.conversations.create({
agent_id: "agent_123",
dynamic_variables: {
user_name: "John",
account_tier: "premium",
order_id: "ORD-12345"
}
});秘密变量(用于API密钥):
{{secret__stripe_api_key}}
{{secret__database_password}}重要提示:秘密变量仅用于请求头,绝不会发送给LLM提供商。
在提示词中使用:
json
{
"agent": {
"prompt": {
"prompt": "You are helping {{user_name}}, a {{account_tier}} customer."
},
"first_message": "Hello {{user_name}}! I see you're calling about order {{order_id}}."
}
}注意事项:缺失变量会导致“缺少必需的动态变量”错误。启动对话时务必提供所有引用的变量。
Authentication Patterns
认证模式
Option 1: Public Agents (No API Key)
typescript
const { startConversation } = useConversation({
agentId: 'your-public-agent-id' // Anyone can use
});Option 2: Private Agents with API Key
typescript
const { startConversation } = useConversation({
agentId: 'your-private-agent-id',
apiKey: process.env.NEXT_PUBLIC_ELEVENLABS_API_KEY
});⚠️ Warning: Never expose API keys in client-side code. Use signed URLs instead.
Option 3: Signed URLs (Recommended for Production)
typescript
// Server-side (Next.js API route)
import { ElevenLabsClient } from 'elevenlabs';
export async function POST(req: Request) {
const client = new ElevenLabsClient({
apiKey: process.env.ELEVENLABS_API_KEY // Server-side only
});
const signedUrl = await client.convai.getSignedUrl({
agent_id: 'your-agent-id'
});
return Response.json({ signedUrl });
}
// Client-side
const { startConversation } = useConversation({
agentId: 'your-agent-id',
signedUrl: await fetch('/api/elevenlabs/auth').then(r => r.json()).then(d => d.signedUrl)
});选项1:公共代理(无需API密钥)
typescript
const { startConversation } = useConversation({
agentId: 'your-public-agent-id' // 任何人都可使用
});选项2:带API密钥的私有代理
typescript
const { startConversation } = useConversation({
agentId: 'your-private-agent-id',
apiKey: process.env.NEXT_PUBLIC_ELEVENLABS_API_KEY
});⚠️ 警告:绝不要在客户端代码中暴露API密钥,请改用签名URL。
选项3:签名URL(生产环境推荐)
typescript
// 服务器端(Next.js API路由)
import { ElevenLabsClient } from 'elevenlabs';
export async function POST(req: Request) {
const client = new ElevenLabsClient({
apiKey: process.env.ELEVENLABS_API_KEY // 仅在服务器端使用
});
const signedUrl = await client.convai.getSignedUrl({
agent_id: 'your-agent-id'
});
return Response.json({ signedUrl });
}
// 客户端
const { startConversation } = useConversation({
agentId: 'your-agent-id',
signedUrl: await fetch('/api/elevenlabs/auth').then(r => r.json()).then(d => d.signedUrl)
});3. Voice & Language Features
3. 语音与语言特性
Multi-Voice Support
多语音支持
Dynamically switch between different voices during a single conversation.
Use Cases:
- Multi-character storytelling (different voice per character)
- Language tutoring (native speaker voices for each language)
- Role-playing scenarios (customer vs agent)
- Emotional agents (different voices for different moods)
Configuration:
json
{
"agent": {
"prompt": {
"prompt": "When speaking as the customer, use voice_id 'customer_voice_abc123'. When speaking as the agent, use voice_id 'agent_voice_def456'."
}
}
}Gotchas:
- Voice switching adds ~200ms latency per switch
- Requires careful prompt engineering to trigger switches correctly
- Not all voices work equally well for all characters
在单次对话中动态切换不同语音。
适用场景:
- 多角色故事讲述(每个角色使用不同语音)
- 语言辅导(每种语言使用母语者语音)
- 角色扮演场景(客户与代理语音)
- 情感化代理(不同情绪使用不同语音)
配置:
json
{
"agent": {
"prompt": {
"prompt": "When speaking as the customer, use voice_id 'customer_voice_abc123'. When speaking as the agent, use voice_id 'agent_voice_def456'."
}
}
}注意事项:
- 语音切换每次会增加约200ms延迟
- 需要精心设计提示词以正确触发切换
- 并非所有语音都适合所有角色
Pronunciation Dictionary
发音词典
Customize how the agent pronounces specific words or phrases.
Supported Formats:
- IPA (International Phonetic Alphabet)
- CMU (Carnegie Mellon University Pronouncing Dictionary)
- Word Substitutions (replace words before TTS)
Configuration:
json
{
"pronunciation_dictionary": [
{
"word": "ElevenLabs",
"pronunciation": "ɪˈlɛvənlæbz",
"format": "ipa"
},
{
"word": "API",
"pronunciation": "ey-pee-ay",
"format": "cmu"
},
{
"word": "AI",
"substitution": "artificial intelligence"
}
]
}Use Cases:
- Brand names (e.g., "IKEA" → "ee-KAY-uh")
- Acronyms (e.g., "API" → "A-P-I" or "ay-pee-eye")
- Technical terms
- Character names in storytelling
Gotcha: Only Turbo v2/v2.5 models support phoneme-based pronunciation. Other models silently skip phoneme entries but still process word substitutions.
自定义代理对特定单词或短语的发音。
支持格式:
- IPA(国际音标)
- CMU(卡内基梅隆大学发音词典)
- 单词替换(TTS前替换单词)
配置:
json
{
"pronunciation_dictionary": [
{
"word": "ElevenLabs",
"pronunciation": "ɪˈlɛvənlæbz",
"format": "ipa"
},
{
"word": "API",
"pronunciation": "ey-pee-ay",
"format": "cmu"
},
{
"word": "AI",
"substitution": "artificial intelligence"
}
]
}适用场景:
- 品牌名称(如“IKEA” → “ee-KAY-uh”)
- 首字母缩写(如“API” → “A-P-I”或“ay-pee-eye”)
- 技术术语
- 故事中的角色名称
注意事项:仅Turbo v2/v2.5模型支持基于音素的发音。其他模型会静默跳过音素条目,但仍会处理单词替换。
Speed Control
语速控制
Adjust speaking speed dynamically (0.7x - 1.2x).
Configuration:
json
{
"voice_settings": {
"speed": 1.0 // 0.7 = slow, 1.0 = normal, 1.2 = fast
}
}Use Cases:
- Slow (0.7x-0.9x): Accessibility, children, non-native speakers
- Normal (1.0x): Default for most use cases
- Fast (1.1x-1.2x): Urgent notifications, power users
Best Practices:
- Use 0.9x-1.1x for natural-sounding adjustments
- Extreme values (below 0.7 or above 1.2) degrade quality
- Speed can be adjusted per agent, not per utterance
动态调整语速(0.7x - 1.2x)。
配置:
json
{
"voice_settings": {
"speed": 1.0 // 0.7 = 慢速, 1.0 = 正常, 1.2 = 快速
}
}适用场景:
- 慢速(0.7x-0.9x):无障碍访问、儿童、非母语使用者
- 正常(1.0x):大多数场景默认设置
- 快速(1.1x-1.2x):紧急通知、高级用户
最佳实践:
- 使用0.9x-1.1x实现自然的语速调整
- 极端值(低于0.7或高于1.2)会降低语音质量
- 语速可按代理配置,无法按单次发言调整
Voice Design
语音设计
Create custom voices using ElevenLabs Voice Design tool.
Workflow:
- Navigate to Voice Library → Create Voice
- Use Voice Design (text-to-voice) or Voice Cloning (sample audio)
- Test voice with sample text
- Save voice to library
- Use in agent configuration
voice_id
Voice Cloning Best Practices:
- Use clean audio samples (no background noise, music, or pops)
- Maintain consistent microphone distance
- Avoid extreme volumes (whispering or shouting)
- 1-2 minutes of audio recommended
Gotcha: Using English-trained voices for non-English languages causes pronunciation issues. Always use language-matched voices.
使用ElevenLabs语音设计工具创建自定义语音。
工作流:
- 导航到语音库 → 创建语音
- 使用语音设计(文本转语音)或语音克隆(样本音频)
- 用示例文本测试语音
- 将语音保存到库中
- 在代理配置中使用
voice_id
语音克隆最佳实践:
- 使用清晰的音频样本(无背景噪音、音乐或爆音)
- 保持麦克风距离一致
- 避免极端音量(低语或大喊)
- 推荐1-2分钟的音频样本
注意事项:将英语训练的语音用于非英语语言会导致发音问题。始终使用与语言匹配的语音。
Language Configuration
语言配置
Support for 32+ languages with automatic detection and in-conversation switching.
Configuration:
json
{
"agent": {
"language": "en" // ISO 639-1 code
}
}Multi-Language Presets (Different Voice Per Language):
json
{
"conversation_config": {
"language_presets": [
{
"language": "en",
"voice_id": "en_voice_id",
"first_message": "Hello! How can I help you today?"
},
{
"language": "es",
"voice_id": "es_voice_id",
"first_message": "¡Hola! ¿Cómo puedo ayudarte hoy?"
},
{
"language": "fr",
"voice_id": "fr_voice_id",
"first_message": "Bonjour! Comment puis-je vous aider aujourd'hui?"
}
]
}
}Automatic Language Detection: Agent detects user's language and switches automatically.
Supported Languages: English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Arabic, Chinese, Japanese, Korean, Hindi, and 18+ more.
支持32+种语言,自动检测并可在对话中切换。
配置:
json
{
"agent": {
"language": "en" // ISO 639-1代码
}
}多语言预设(每种语言使用不同语音):
json
{
"conversation_config": {
"language_presets": [
{
"language": "en",
"voice_id": "en_voice_id",
"first_message": "Hello! How can I help you today?"
},
{
"language": "es",
"voice_id": "es_voice_id",
"first_message": "¡Hola! ¿Cómo puedo ayudarte hoy?"
},
{
"language": "fr",
"voice_id": "fr_voice_id",
"first_message": "Bonjour! Comment puis-je vous aider aujourd'hui?"
}
]
}
}自动语言检测:代理检测用户语言并自动切换。
支持语言:英语、西班牙语、法语、德语、意大利语、葡萄牙语、荷兰语、波兰语、阿拉伯语、中文、日语、韩语、印地语及18+种其他语言。
4. Knowledge Base & RAG
4. 知识库与RAG
RAG (Retrieval-Augmented Generation)
RAG(检索增强生成)
Enable agents to access large knowledge bases without loading entire documents into context.
How It Works:
- Upload documents (PDF, TXT, DOCX) to knowledge base
- ElevenLabs automatically computes vector embeddings
- During conversation, relevant chunks retrieved based on semantic similarity
- LLM uses retrieved context to generate responses
Configuration:
json
{
"agent": {
"prompt": {
"knowledge_base": ["doc_id_1", "doc_id_2"]
}
}
}Upload Documents via API:
typescript
import { ElevenLabsClient } from 'elevenlabs';
const client = new ElevenLabsClient({ apiKey: process.env.ELEVENLABS_API_KEY });
// Upload document
const doc = await client.knowledgeBase.upload({
file: fs.createReadStream('support_docs.pdf'),
name: 'Support Documentation'
});
// Compute RAG index
await client.knowledgeBase.computeRagIndex({
document_id: doc.id,
embedding_model: 'e5_mistral_7b' // or 'multilingual_e5_large'
});Retrieval Configuration:
json
{
"knowledge_base_config": {
"max_chunks": 5, // Number of chunks to retrieve
"vector_distance_threshold": 0.8 // Similarity threshold
}
}Use Cases:
- Product documentation agents
- Customer support (FAQ, help center)
- Educational tutors (textbooks, lecture notes)
- Healthcare assistants (medical guidelines)
Gotchas:
- RAG adds ~500ms latency per query
- More chunks = higher cost but better context
- Higher vector distance = more context but potentially less relevant
- Documents must be indexed before use (can take minutes for large docs)
使代理无需加载整个文档到上下文即可访问大型知识库。
工作原理:
- 将文档(PDF、TXT、DOCX)上传到知识库
- ElevenLabs自动计算向量嵌入
- 对话过程中,基于语义相似度检索相关片段
- LLM使用检索到的上下文生成响应
配置:
json
{
"agent": {
"prompt": {
"knowledge_base": ["doc_id_1", "doc_id_2"]
}
}
}通过API上传文档:
typescript
import { ElevenLabsClient } from 'elevenlabs';
const client = new ElevenLabsClient({ apiKey: process.env.ELEVENLABS_API_KEY });
// 上传文档
const doc = await client.knowledgeBase.upload({
file: fs.createReadStream('support_docs.pdf'),
name: 'Support Documentation'
});
// 计算RAG索引
await client.knowledgeBase.computeRagIndex({
document_id: doc.id,
embedding_model: 'e5_mistral_7b' // 或 'multilingual_e5_large'
});检索配置:
json
{
"knowledge_base_config": {
"max_chunks": 5, // 检索的片段数量
"vector_distance_threshold": 0.8 // 相似度阈值
}
}适用场景:
- 产品文档代理
- 客户支持(FAQ、帮助中心)
- 教育辅导(教材、讲义)
- 医疗助手(医疗指南)
注意事项:
- RAG每次查询会增加约500ms延迟
- 片段越多,成本越高但上下文越全面
- 向量距离阈值越高,上下文越全面但相关性可能降低
- 文档必须先索引才能使用(大型文档可能需要数分钟)
5. Tools (4 Types)
5. 工具(4种类型)
ElevenLabs supports 4 distinct tool types, each with different execution patterns.
ElevenLabs支持4种不同类型的工具,每种有不同的执行模式。
A. Client Tools
A. 客户端工具
Execute operations on the client side (browser or mobile app).
Use Cases:
- Update UI elements (shopping cart, notifications)
- Trigger navigation (redirect user to page)
- Access local storage
- Control media playback
React Example:
typescript
import { useConversation } from '@elevenlabs/react';
import { z } from 'zod';
const { startConversation } = useConversation({
clientTools: {
updateCart: {
description: "Update the shopping cart with new items",
parameters: z.object({
item: z.string().describe("The item name"),
quantity: z.number().describe("Quantity to add")
}),
handler: async ({ item, quantity }) => {
// Client-side logic
const cart = getCart();
cart.add(item, quantity);
updateUI(cart);
return { success: true, total: cart.total };
}
},
navigate: {
description: "Navigate to a different page",
parameters: z.object({
url: z.string().describe("The URL to navigate to")
}),
handler: async ({ url }) => {
window.location.href = url;
return { success: true };
}
}
}
});Gotchas:
- Tool names are case-sensitive
- Must return a value (agent reads the return value)
- Handler can be async
在客户端(浏览器或移动应用)执行操作。
适用场景:
- 更新UI元素(购物车、通知)
- 触发导航(重定向用户到页面)
- 访问本地存储
- 控制媒体播放
React示例:
typescript
import { useConversation } from '@elevenlabs/react';
import { z } from 'zod';
const { startConversation } = useConversation({
clientTools: {
updateCart: {
description: "Update the shopping cart with new items",
parameters: z.object({
item: z.string().describe("The item name"),
quantity: z.number().describe("Quantity to add")
}),
handler: async ({ item, quantity }) => {
// 客户端逻辑
const cart = getCart();
cart.add(item, quantity);
updateUI(cart);
return { success: true, total: cart.total };
}
},
navigate: {
description: "Navigate to a different page",
parameters: z.object({
url: z.string().describe("The URL to navigate to")
}),
handler: async ({ url }) => {
window.location.href = url;
return { success: true };
}
}
}
});注意事项:
- 工具名称大小写敏感
- 必须返回值(代理会读取返回值)
- 处理器可以是异步函数
B. Server Tools (Webhooks)
B. 服务器工具(Webhooks)
Make HTTP requests to external APIs from ElevenLabs servers.
Use Cases:
- Fetch real-time data (weather, stock prices)
- Update CRM systems (Salesforce, HubSpot)
- Process payments (Stripe, PayPal)
- Send emails/SMS (SendGrid, Twilio)
Configuration via CLI:
bash
elevenlabs tools add-webhook "Get Weather" --config-path tool_configs/get-weather.jsontool_configs/get-weather.json:
json
{
"name": "get_weather",
"description": "Fetch current weather for a city",
"url": "https://api.weather.com/v1/current",
"method": "GET",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city name (e.g., 'London', 'New York')"
}
},
"required": ["city"]
},
"headers": {
"Authorization": "Bearer {{secret__weather_api_key}}"
}
}Dynamic Variables in Tools:
json
{
"url": "https://api.crm.com/customers/{{user_id}}",
"headers": {
"X-API-Key": "{{secret__crm_api_key}}"
}
}Gotchas:
- Secret variables only work in headers (not URL or body)
- Schema description guides LLM on when to use tool
从ElevenLabs服务器向外部API发起HTTP请求。
适用场景:
- 获取实时数据(天气、股价)
- 更新CRM系统(Salesforce、HubSpot)
- 处理支付(Stripe、PayPal)
- 发送邮件/SMS(SendGrid、Twilio)
通过CLI配置:
bash
elevenlabs tools add-webhook "Get Weather" --config-path tool_configs/get-weather.jsontool_configs/get-weather.json:
json
{
"name": "get_weather",
"description": "Fetch current weather for a city",
"url": "https://api.weather.com/v1/current",
"method": "GET",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city name (e.g., 'London', 'New York')"
}
},
"required": ["city"]
},
"headers": {
"Authorization": "Bearer {{secret__weather_api_key}}"
}
}工具中的动态变量:
json
{
"url": "https://api.crm.com/customers/{{user_id}}",
"headers": {
"X-API-Key": "{{secret__crm_api_key}}"
}
}注意事项:
- 秘密变量仅在请求头中生效(不在URL或请求体中)
- 架构描述指导LLM何时使用工具
C. MCP Tools (Model Context Protocol)
C. MCP工具(模型上下文协议)
Connect to external MCP servers for standardized tool access.
Use Cases:
- Access databases (PostgreSQL, MongoDB)
- Query knowledge bases (Pinecone, Weaviate)
- Integrate with IDEs (VS Code, Cursor)
- Connect to data sources (Google Drive, Notion)
Configuration:
- Navigate to MCP server integrations in dashboard
- Click "Add Custom MCP Server"
- Configure:
- Name: Server identifier
- Server URL: SSE or HTTP endpoint
- Secret Token: Optional auth header
- Test connectivity and discover tools
- Add to agents (public or private)
Approval Modes:
- Always Ask: Maximum security, requires permission per tool call
- Fine-Grained: Per-tool approval settings
- No Approval: Auto-execute all tools
Gotchas:
- Only SSE and HTTP streamable transport supported
- MCP servers must be publicly accessible or behind auth
- Not available for Zero Retention Mode
- Not compatible with HIPAA compliance
Example: Using ElevenLabs MCP Server in Claude Desktop:
json
{
"mcpServers": {
"ElevenLabs": {
"command": "uvx",
"args": ["elevenlabs-mcp"],
"env": {
"ELEVENLABS_API_KEY": "<your-key>",
"ELEVENLABS_MCP_OUTPUT_MODE": "files"
}
}
}
}连接到外部MCP服务器以标准化访问工具。
适用场景:
- 访问数据库(PostgreSQL、MongoDB)
- 查询知识库(Pinecone、Weaviate)
- 集成IDE(VS Code、Cursor)
- 连接数据源(Google Drive、Notion)
配置:
- 在仪表板中导航到MCP服务器集成
- 点击“添加自定义MCP服务器”
- 配置:
- 名称:服务器标识符
- 服务器URL:SSE或HTTP端点
- 秘密令牌:可选的认证头
- 测试连接并发现工具
- 添加到代理(公共或私有)
审批模式:
- 始终询问:最高安全性,每次工具调用需权限
- 细粒度:按工具设置审批权限
- 无需审批:自动执行所有工具
注意事项:
- 仅支持SSE和HTTP可流式传输协议
- MCP服务器必须公开可访问或带认证
- 零保留模式下不可用
- 与HIPAA合规不兼容
示例:在Claude Desktop中使用ElevenLabs MCP服务器:
json
{
"mcpServers": {
"ElevenLabs": {
"command": "uvx",
"args": ["elevenlabs-mcp"],
"env": {
"ELEVENLABS_API_KEY": "<your-key>",
"ELEVENLABS_MCP_OUTPUT_MODE": "files"
}
}
}
}D. System Tools
D. 系统工具
Modify the internal state of the conversation without external calls.
Use Cases:
- Update conversation context
- Switch between workflow nodes
- Modify agent behavior mid-conversation
- Track conversation state
Built-in System Tools:
- - End the conversation
end_call - - Detect user's language
detect_language - - Switch to different agent/workflow node
transfer_agent - - Transfer to external phone number (telephony only)
transfer_to_number - - Display DTMF keypad (telephony only)
dtmf_playpad - - Detect voicemail (telephony only)
voicemail_detection
Configuration:
json
{
"system_tools": [
{
"name": "update_conversation_state",
"description": "Update the conversation context with new information",
"parameters": {
"key": { "type": "string" },
"value": { "type": "string" }
}
}
]
}Gotchas:
- System tools don't trigger external APIs
- Changes are ephemeral (lost after conversation ends)
- Useful for workflows and state management
无需外部调用即可修改对话的内部状态。
适用场景:
- 更新对话上下文
- 在工作流节点间切换
- 对话过程中修改代理行为
- 跟踪对话状态
内置系统工具:
- - 结束对话
end_call - - 检测用户语言
detect_language - - 切换到不同代理/工作流节点
transfer_agent - - 转接至外部电话号码(仅电话系统)
transfer_to_number - - 显示DTMF键盘(仅电话系统)
dtmf_playpad - - 检测语音信箱(仅电话系统)
voicemail_detection
配置:
json
{
"system_tools": [
{
"name": "update_conversation_state",
"description": "Update the conversation context with new information",
"parameters": {
"key": { "type": "string" },
"value": { "type": "string" }
}
}
]
}注意事项:
- 系统工具不会触发外部API
- 更改是临时的(对话结束后丢失)
- 适用于工作流和状态管理
6. SDK Integration
6. SDK集成
React SDK (@elevenlabs/react
)
@elevenlabs/reactReact SDK (@elevenlabs/react
)
@elevenlabs/reactInstallation:
bash
npm install @elevenlabs/react zodComplete Example:
typescript
import { useConversation } from '@elevenlabs/react';
import { z } from 'zod';
import { useState } from 'react';
export default function VoiceAgent() {
const [transcript, setTranscript] = useState<string[]>([]);
const {
startConversation,
stopConversation,
status,
isSpeaking
} = useConversation({
agentId: 'your-agent-id',
// Authentication (choose one)
apiKey: process.env.NEXT_PUBLIC_ELEVENLABS_API_KEY,
// Client tools
clientTools: {
updateCart: {
description: "Update shopping cart",
parameters: z.object({
item: z.string(),
quantity: z.number()
}),
handler: async ({ item, quantity }) => {
console.log('Cart updated:', item, quantity);
return { success: true };
}
}
},
// Events
onConnect: () => {
console.log('Connected to agent');
setTranscript([]);
},
onDisconnect: () => console.log('Disconnected'),
onEvent: (event) => {
if (event.type === 'transcript') {
setTranscript(prev => [...prev, `User: ${event.data.text}`]);
} else if (event.type === 'agent_response') {
setTranscript(prev => [...prev, `Agent: ${event.data.text}`]);
}
},
onError: (error) => console.error('Error:', error),
// Regional compliance
serverLocation: 'us'
});
return (
<div>
<div>
<button onClick={startConversation} disabled={status === 'connected'}>
Start Conversation
</button>
<button onClick={stopConversation} disabled={status !== 'connected'}>
Stop
</button>
</div>
<div>Status: {status}</div>
<div>{isSpeaking && 'Agent is speaking...'}</div>
<div>
<h3>Transcript</h3>
{transcript.map((line, i) => (
<p key={i}>{line}</p>
))}
</div>
</div>
);
}安装:
bash
npm install @elevenlabs/react zod完整示例:
typescript
import { useConversation } from '@elevenlabs/react';
import { z } from 'zod';
import { useState } from 'react';
export default function VoiceAgent() {
const [transcript, setTranscript] = useState<string[]>([]);
const {
startConversation,
stopConversation,
status,
isSpeaking
} = useConversation({
agentId: 'your-agent-id',
// 认证(选择一种)
apiKey: process.env.NEXT_PUBLIC_ELEVENLABS_API_KEY,
// 客户端工具
clientTools: {
updateCart: {
description: "Update shopping cart",
parameters: z.object({
item: z.string(),
quantity: z.number()
}),
handler: async ({ item, quantity }) => {
console.log('Cart updated:', item, quantity);
return { success: true };
}
}
},
// 事件
onConnect: () => {
console.log('Connected to agent');
setTranscript([]);
},
onDisconnect: () => console.log('Disconnected'),
onEvent: (event) => {
if (event.type === 'transcript') {
setTranscript(prev => [...prev, `User: ${event.data.text}`]);
} else if (event.type === 'agent_response') {
setTranscript(prev => [...prev, `Agent: ${event.data.text}`]);
}
},
onError: (error) => console.error('Error:', error),
// 区域合规
serverLocation: 'us'
});
return (
<div>
<div>
<button onClick={startConversation} disabled={status === 'connected'}>
Start Conversation
</button>
<button onClick={stopConversation} disabled={status !== 'connected'}>
Stop
</button>
</div>
<div>Status: {status}</div>
<div>{isSpeaking && 'Agent is speaking...'}</div>
<div>
<h3>Transcript</h3>
{transcript.map((line, i) => (
<p key={i}>{line}</p>
))}
</div>
</div>
);
}JavaScript SDK (@elevenlabs/client
)
@elevenlabs/clientJavaScript SDK (@elevenlabs/client
)
@elevenlabs/clientFor vanilla JavaScript projects (no React).
Installation:
bash
npm install @elevenlabs/clientExample:
javascript
import { Conversation } from '@elevenlabs/client';
const conversation = new Conversation({
agentId: 'your-agent-id',
apiKey: process.env.ELEVENLABS_API_KEY,
onConnect: () => console.log('Connected'),
onDisconnect: () => console.log('Disconnected'),
onEvent: (event) => {
switch (event.type) {
case 'transcript':
document.getElementById('user-text').textContent = event.data.text;
break;
case 'agent_response':
document.getElementById('agent-text').textContent = event.data.text;
break;
}
}
});
// Start conversation
document.getElementById('start-btn').addEventListener('click', async () => {
await conversation.start();
});
// Stop conversation
document.getElementById('stop-btn').addEventListener('click', async () => {
await conversation.stop();
});适用于纯JavaScript项目(无React)。
安装:
bash
npm install @elevenlabs/client示例:
javascript
import { Conversation } from '@elevenlabs/client';
const conversation = new Conversation({
agentId: 'your-agent-id',
apiKey: process.env.ELEVENLABS_API_KEY,
onConnect: () => console.log('Connected'),
onDisconnect: () => console.log('Disconnected'),
onEvent: (event) => {
switch (event.type) {
case 'transcript':
document.getElementById('user-text').textContent = event.data.text;
break;
case 'agent_response':
document.getElementById('agent-text').textContent = event.data.text;
break;
}
}
});
// 启动对话
document.getElementById('start-btn').addEventListener('click', async () => {
await conversation.start();
});
// 停止对话
document.getElementById('stop-btn').addEventListener('click', async () => {
await conversation.stop();
});Connection Types: WebRTC vs WebSocket
连接类型:WebRTC vs WebSocket
ElevenLabs SDKs support two connection types with different characteristics.
Comparison Table:
| Feature | WebSocket | WebRTC |
|---|---|---|
| Authentication | | |
| Audio Format | Configurable | PCM_48000 (hardcoded) |
| Sample Rate | Configurable (16k, 24k, 48k) | 48000 (hardcoded) |
| Latency | Standard | Lower |
| Device Switching | Flexible | Limited (format locked) |
| Best For | General use, flexibility | Low-latency requirements |
WebSocket Configuration (default):
typescript
import { useConversation } from '@elevenlabs/react';
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// WebSocket uses signed URL
signedUrl: async () => {
const response = await fetch('/api/elevenlabs/auth');
const { signedUrl } = await response.json();
return signedUrl;
},
// Connection type (optional, defaults to 'websocket')
connectionType: 'websocket',
// Audio config (flexible)
audioConfig: {
sampleRate: 24000, // 16000, 24000, or 48000
format: 'PCM_24000'
}
});WebRTC Configuration:
typescript
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// WebRTC uses conversation token (different auth flow)
conversationToken: async () => {
const response = await fetch('/api/elevenlabs/token');
const { token } = await response.json();
return token;
},
// Connection type
connectionType: 'webrtc',
// Audio format is HARDCODED to PCM_48000 (not configurable)
// audioConfig ignored for WebRTC
});Backend Token Endpoints:
typescript
// WebSocket signed URL (GET /v1/convai/conversation/get-signed-url)
app.get('/api/elevenlabs/auth', async (req, res) => {
const response = await fetch(
`https://api.elevenlabs.io/v1/convai/conversation/get-signed-url?agent_id=${AGENT_ID}`,
{ headers: { 'xi-api-key': ELEVENLABS_API_KEY } }
);
const { signed_url } = await response.json();
res.json({ signedUrl: signed_url });
});
// WebRTC conversation token (GET /v1/convai/conversation/token)
app.get('/api/elevenlabs/token', async (req, res) => {
const response = await fetch(
`https://api.elevenlabs.io/v1/convai/conversation/token?agent_id=${AGENT_ID}`,
{ headers: { 'xi-api-key': ELEVENLABS_API_KEY } }
);
const { conversation_token } = await response.json();
res.json({ token: conversation_token });
});When to Use Each:
| Use WebSocket When | Use WebRTC When |
|---|---|
| Need flexible audio formats | Need lowest possible latency |
| Switching between audio devices frequently | Audio format can be locked to 48kHz |
| Standard latency is acceptable | Building real-time applications |
| Need maximum configuration control | Performance is critical |
Gotchas:
- WebRTC hardcodes PCM_48000 - no way to change format
- Device switching in WebRTC limited by fixed format
- Different authentication methods (signedUrl vs conversationToken)
- WebRTC may have better performance but less flexibility
ElevenLabs SDK支持两种连接类型,各有不同特性。
对比表:
| 特性 | WebSocket | WebRTC |
|---|---|---|
| 认证 | | |
| 音频格式 | 可配置 | PCM_48000(硬编码) |
| 采样率 | 可配置(16k、24k、48k) | 48000(硬编码) |
| 延迟 | 标准 | 更低 |
| 设备切换 | 灵活 | 受限(格式锁定) |
| 最佳场景 | 通用场景、灵活性 | 低延迟需求 |
WebSocket配置(默认):
typescript
import { useConversation } from '@elevenlabs/react';
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// WebSocket使用签名URL
signedUrl: async () => {
const response = await fetch('/api/elevenlabs/auth');
const { signedUrl } = await response.json();
return signedUrl;
},
// 连接类型(可选,默认'websocket')
connectionType: 'websocket',
// 音频配置(灵活)
audioConfig: {
sampleRate: 24000, // 16000、24000或48000
format: 'PCM_24000'
}
});WebRTC配置:
typescript
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// WebRTC使用对话令牌(不同的认证流程)
conversationToken: async () => {
const response = await fetch('/api/elevenlabs/token');
const { token } = await response.json();
return token;
},
// 连接类型
connectionType: 'webrtc',
// 音频格式硬编码为PCM_48000(不可配置)
// audioConfig对WebRTC无效
});后端令牌端点:
typescript
// WebSocket签名URL(GET /v1/convai/conversation/get-signed-url)
app.get('/api/elevenlabs/auth', async (req, res) => {
const response = await fetch(
`https://api.elevenlabs.io/v1/convai/conversation/get-signed-url?agent_id=${AGENT_ID}`,
{ headers: { 'xi-api-key': ELEVENLABS_API_KEY } }
);
const { signed_url } = await response.json();
res.json({ signedUrl: signed_url });
});
// WebRTC对话令牌(GET /v1/convai/conversation/token)
app.get('/api/elevenlabs/token', async (req, res) => {
const response = await fetch(
`https://api.elevenlabs.io/v1/convai/conversation/token?agent_id=${AGENT_ID}`,
{ headers: { 'xi-api-key': ELEVENLABS_API_KEY } }
);
const { conversation_token } = await response.json();
res.json({ token: conversation_token });
});何时使用哪种类型:
| 使用WebSocket的场景 | 使用WebRTC的场景 |
|---|---|
| 需要灵活的音频格式 | 需要最低延迟 |
| 频繁切换音频设备 | 音频格式可锁定为48kHz |
| 标准延迟可接受 | 构建实时应用 |
| 需要最大配置控制权 | 性能至关重要 |
注意事项:
- WebRTC硬编码PCM_48000,无法更改格式
- WebRTC中设备切换受固定格式限制
- 不同的认证方式(signedUrl vs conversationToken)
- WebRTC性能更好但灵活性更低
React Native SDK (Expo)
React Native SDK(Expo)
Installation:
bash
npx expo install @elevenlabs/react-native @livekit/react-native @livekit/react-native-webrtc livekit-clientRequirements:
- Expo SDK 47+
- iOS 14.0+ / macOS 11.0+
- Custom dev build required (Expo Go not supported)
Example:
typescript
import { useConversation } from '@elevenlabs/react-native';
import { View, Button, Text } from 'react-native';
import { z } from 'zod';
export default function App() {
const { startConversation, stopConversation, status } = useConversation({
agentId: 'your-agent-id',
signedUrl: 'https://api.elevenlabs.io/v1/convai/auth/...',
clientTools: {
updateProfile: {
description: "Update user profile",
parameters: z.object({
name: z.string()
}),
handler: async ({ name }) => {
console.log('Updating profile:', name);
return { success: true };
}
}
}
});
return (
<View style={{ padding: 20 }}>
<Button title="Start" onPress={startConversation} />
<Button title="Stop" onPress={stopConversation} />
<Text>Status: {status}</Text>
</View>
);
}Gotchas:
- Requires custom dev build (not Expo Go)
- iOS/macOS only (Android support via Kotlin SDK, not yet officially released)
安装:
bash
npx expo install @elevenlabs/react-native @livekit/react-native @livekit/react-native-webrtc livekit-client要求:
- Expo SDK 47+
- iOS 14.0+ / macOS 11.0+
- 需要自定义开发构建(不支持Expo Go)
示例:
typescript
import { useConversation } from '@elevenlabs/react-native';
import { View, Button, Text } from 'react-native';
import { z } from 'zod';
export default function App() {
const { startConversation, stopConversation, status } = useConversation({
agentId: 'your-agent-id',
signedUrl: 'https://api.elevenlabs.io/v1/convai/auth/...',
clientTools: {
updateProfile: {
description: "Update user profile",
parameters: z.object({
name: z.string()
}),
handler: async ({ name }) => {
console.log('Updating profile:', name);
return { success: true };
}
}
}
});
return (
<View style={{ padding: 20 }}>
<Button title="Start" onPress={startConversation} />
<Button title="Stop" onPress={stopConversation} />
<Text>Status: {status}</Text>
</View>
);
}注意事项:
- 需要自定义开发构建(不支持Expo Go)
- 仅支持iOS/macOS(Android支持通过Kotlin SDK,尚未正式发布)
Swift SDK (iOS/macOS)
Swift SDK(iOS/macOS)
Installation (Swift Package Manager):
swift
dependencies: [
.package(url: "https://github.com/elevenlabs/elevenlabs-swift-sdk", from: "1.0.0")
]Requirements:
- iOS 14.0+ / macOS 11.0+
- Swift 5.9+
Use Cases:
- Native iOS apps
- macOS applications
- watchOS (with limitations)
安装(Swift Package Manager):
swift
dependencies: [
.package(url: "https://github.com/elevenlabs/elevenlabs-swift-sdk", from: "1.0.0")
]要求:
- iOS 14.0+ / macOS 11.0+
- Swift 5.9+
适用场景:
- 原生iOS应用
- macOS应用
- watchOS(有限支持)
Widget (Embeddable Web Component)
组件(可嵌入Web组件)
Installation:
Copy-paste embed code from dashboard or use this template:
html
<script src="https://elevenlabs.io/convai-widget/index.js"></script>
<script>
ElevenLabsWidget.init({
agentId: 'your-agent-id',
// Theming
theme: {
primaryColor: '#3B82F6',
backgroundColor: '#1F2937',
textColor: '#F9FAFB'
},
// Position
position: 'bottom-right', // 'bottom-left' | 'bottom-right'
// Custom branding
branding: {
logo: 'https://example.com/logo.png',
name: 'Support Agent'
}
});
</script>Use Cases:
- Customer support chat bubbles
- Website assistants
- Lead capture forms
安装:
从仪表板复制嵌入代码或使用以下模板:
html
<script src="https://elevenlabs.io/convai-widget/index.js"></script>
<script>
ElevenLabsWidget.init({
agentId: 'your-agent-id',
// 主题
theme: {
primaryColor: '#3B82F6',
backgroundColor: '#1F2937',
textColor: '#F9FAFB'
},
// 位置
position: 'bottom-right', // 'bottom-left' | 'bottom-right'
// 自定义品牌
branding: {
logo: 'https://example.com/logo.png',
name: 'Support Agent'
}
});
</script>适用场景:
- 客户支持聊天气泡
- 网站助手
- 潜在客户捕获表单
Scribe (Real-Time Speech-to-Text)
Scribe(实时语音转文本)
Status: Closed Beta (requires sales contact)
Release: 2025
Scribe is ElevenLabs' real-time speech-to-text service for low-latency transcription.
Capabilities:
- Microphone streaming (real-time transcription)
- Pre-recorded audio file transcription
- Partial (interim) and final transcripts
- Word-level timestamps
- Voice Activity Detection (VAD)
- Manual and automatic commit strategies
- Language detection
- PCM_16000 and PCM_24000 audio formats
Authentication:
Uses single-use tokens (not API keys):
typescript
// Fetch token from backend
const response = await fetch('/api/scribe/token');
const { token } = await response.json();
// Backend endpoint
const token = await client.scribe.getToken();
return { token };React Hook ():
useScribetypescript
import { useScribe } from '@elevenlabs/react';
export default function Transcription() {
const {
connect,
disconnect,
startRecording,
stopRecording,
status,
transcript,
partialTranscript
} = useScribe({
token: async () => {
const response = await fetch('/api/scribe/token');
const { token } = await response.json();
return token;
},
// Commit strategy
commitStrategy: 'vad', // 'vad' (automatic) or 'manual'
// Audio format
sampleRate: 16000, // 16000 or 24000
// Events
onConnect: () => console.log('Connected to Scribe'),
onDisconnect: () => console.log('Disconnected'),
onPartialTranscript: (text) => {
console.log('Interim:', text);
},
onFinalTranscript: (text, timestamps) => {
console.log('Final:', text);
console.log('Timestamps:', timestamps); // Word-level timing
},
onError: (error) => console.error('Error:', error)
});
return (
<div>
<button onClick={connect}>Connect</button>
<button onClick={startRecording}>Start Recording</button>
<button onClick={stopRecording}>Stop Recording</button>
<button onClick={disconnect}>Disconnect</button>
<p>Status: {status}</p>
<p>Partial: {partialTranscript}</p>
<p>Final: {transcript}</p>
</div>
);
}JavaScript SDK ():
Scribe.connectjavascript
import { Scribe } from '@elevenlabs/client';
const connection = await Scribe.connect({
token: 'your-single-use-token',
sampleRate: 16000,
commitStrategy: 'vad',
onPartialTranscript: (text) => {
document.getElementById('interim').textContent = text;
},
onFinalTranscript: (text, timestamps) => {
const finalDiv = document.getElementById('final');
finalDiv.textContent += text + ' ';
// timestamps: [{ word: 'hello', start: 0.5, end: 0.8 }, ...]
},
onError: (error) => {
console.error('Scribe error:', error);
}
});
// Start recording from microphone
await connection.startRecording();
// Stop recording
await connection.stopRecording();
// Manual commit (if commitStrategy: 'manual')
await connection.commit();
// Disconnect
await connection.disconnect();Transcribing Pre-Recorded Files:
typescript
import { Scribe } from '@elevenlabs/client';
const connection = await Scribe.connect({ token });
// Send audio buffer
const audioBuffer = fs.readFileSync('recording.pcm');
await connection.sendAudioData(audioBuffer);
// Manually commit to get final transcript
await connection.commit();
// Wait for final transcript eventEvent Types:
- : Connection established
SESSION_STARTED - : Interim transcription (unbuffered)
PARTIAL_TRANSCRIPT - : Complete sentence/phrase
FINAL_TRANSCRIPT - : Final + word timing
FINAL_TRANSCRIPT_WITH_TIMESTAMPS - : Transcription error
ERROR - : Authentication failed
AUTH_ERROR - : WebSocket opened
OPEN - : WebSocket closed
CLOSE
Commit Strategies:
| Strategy | Description | Use When |
|---|---|---|
| Voice Activity Detection auto-commits on silence | Real-time transcription |
| Call | Pre-recorded files, controlled commits |
Audio Formats:
- (16kHz, 16-bit PCM)
PCM_16000 - (24kHz, 16-bit PCM)
PCM_24000
Gotchas:
- Token is single-use (expires after one connection)
- Closed beta - requires sales contact
- Language detection automatic (no manual override)
- No speaker diarization yet
When to Use Scribe:
- Building custom transcription UI
- Real-time captions/subtitles
- Voice note apps
- Meeting transcription
- Accessibility features
When NOT to Use:
Use Agents Platform instead if you need:
- Conversational AI (LLM + TTS)
- Two-way voice interaction
- Agent responses
状态:封闭测试版(需联系销售)
发布时间:2025年
Scribe是ElevenLabs的实时语音转文本服务,实现低延迟转录。
能力:
- 麦克风流(实时转录)
- 预录制音频文件转录
- 部分(临时)和最终转录本
- 单词级时间戳
- 语音活动检测(VAD)
- 手动和自动提交策略
- 语言检测
- PCM_16000和PCM_24000音频格式
认证:
使用一次性令牌(不使用API密钥):
typescript
// 从后端获取令牌
const response = await fetch('/api/scribe/token');
const { token } = await response.json();
// 后端端点
const token = await client.scribe.getToken();
return { token };React Hook ():
useScribetypescript
import { useScribe } from '@elevenlabs/react';
export default function Transcription() {
const {
connect,
disconnect,
startRecording,
stopRecording,
status,
transcript,
partialTranscript
} = useScribe({
token: async () => {
const response = await fetch('/api/scribe/token');
const { token } = await response.json();
return token;
},
// 提交策略
commitStrategy: 'vad', // 'vad'(自动)或 'manual'
// 音频格式
sampleRate: 16000, // 16000或24000
// 事件
onConnect: () => console.log('Connected to Scribe'),
onDisconnect: () => console.log('Disconnected'),
onPartialTranscript: (text) => {
console.log('Interim:', text);
},
onFinalTranscript: (text, timestamps) => {
console.log('Final:', text);
console.log('Timestamps:', timestamps); // 单词级时间
},
onError: (error) => console.error('Error:', error)
});
return (
<div>
<button onClick={connect}>Connect</button>
<button onClick={startRecording}>Start Recording</button>
<button onClick={stopRecording}>Stop Recording</button>
<button onClick={disconnect}>Disconnect</button>
<p>Status: {status}</p>
<p>Partial: {partialTranscript}</p>
<p>Final: {transcript}</p>
</div>
);
}JavaScript SDK ():
Scribe.connectjavascript
import { Scribe } from '@elevenlabs/client';
const connection = await Scribe.connect({
token: 'your-single-use-token',
sampleRate: 16000,
commitStrategy: 'vad',
onPartialTranscript: (text) => {
document.getElementById('interim').textContent = text;
},
onFinalTranscript: (text, timestamps) => {
const finalDiv = document.getElementById('final');
finalDiv.textContent += text + ' ';
// timestamps: [{ word: 'hello', start: 0.5, end: 0.8 }, ...]
},
onError: (error) => {
console.error('Scribe error:', error);
}
});
// 开始从麦克风录制
await connection.startRecording();
// 停止录制
await connection.stopRecording();
// 手动提交(若commitStrategy: 'manual')
await connection.commit();
// 断开连接
await connection.disconnect();转录预录制文件:
typescript
import { Scribe } from '@elevenlabs/client';
const connection = await Scribe.connect({ token });
// 发送音频缓冲区
const audioBuffer = fs.readFileSync('recording.pcm');
await connection.sendAudioData(audioBuffer);
// 手动提交获取最终转录本
await connection.commit();
// 等待最终转录本事件事件类型:
- :连接建立
SESSION_STARTED - :临时转录(无缓冲)
PARTIAL_TRANSCRIPT - :完整句子/短语
FINAL_TRANSCRIPT - :最终转录本+单词时间
FINAL_TRANSCRIPT_WITH_TIMESTAMPS - :转录错误
ERROR - :认证失败
AUTH_ERROR - :WebSocket打开
OPEN - :WebSocket关闭
CLOSE
提交策略:
| 策略 | 描述 | 适用场景 |
|---|---|---|
| 语音活动检测在静音时自动提交 | 实时转录 |
| 显式调用 | 预录制文件、受控提交 |
音频格式:
- (16kHz,16位PCM)
PCM_16000 - (24kHz,16位PCM)
PCM_24000
注意事项:
- 令牌是一次性的(一次连接后过期)
- 封闭测试版,需联系销售
- 语言检测自动进行(无手动覆盖)
- 尚不支持说话人分离
何时使用Scribe:
- 构建自定义转录UI
- 实时字幕/副标题
- 语音笔记应用
- 会议转录
- 无障碍功能
何时不使用:
若需要以下功能,请使用Agents Platform:
- 对话式AI(LLM + TTS)
- 双向语音交互
- 代理响应
7. Testing & Evaluation
7. 测试与评估
Scenario Testing (LLM-Based Evaluation)
场景测试(基于LLM的评估)
Simulate full conversations and evaluate against success criteria.
Configuration via CLI:
bash
elevenlabs tests add "Refund Request Test" --template basic-llmtest_configs/refund-request-test.json:
json
{
"name": "Refund Request Test",
"scenario": "Customer requests refund for defective product",
"user_input": "I want a refund for order #12345. The product was broken when it arrived.",
"success_criteria": [
"Agent acknowledges the request empathetically",
"Agent asks for order number (which was already provided)",
"Agent verifies order details",
"Agent provides refund timeline or next steps"
],
"evaluation_type": "llm"
}Run Test:
bash
elevenlabs agents test "Support Agent"模拟完整对话并根据成功标准评估。
通过CLI配置:
bash
elevenlabs tests add "Refund Request Test" --template basic-llmtest_configs/refund-request-test.json:
json
{
"name": "Refund Request Test",
"scenario": "Customer requests refund for defective product",
"user_input": "I want a refund for order #12345. The product was broken when it arrived.",
"success_criteria": [
"Agent acknowledges the request empathetically",
"Agent asks for order number (which was already provided)",
"Agent verifies order details",
"Agent provides refund timeline or next steps"
],
"evaluation_type": "llm"
}运行测试:
bash
elevenlabs agents test "Support Agent"Tool Call Testing
工具调用测试
Verify that agents correctly use tools with the right parameters.
Configuration:
json
{
"name": "Account Balance Test",
"scenario": "Customer requests account balance",
"expected_tool_call": {
"tool_name": "get_account_balance",
"parameters": {
"account_id": "ACC-12345"
}
}
}验证代理是否正确使用工具并传入正确参数。
配置:
json
{
"name": "Account Balance Test",
"scenario": "Customer requests account balance",
"expected_tool_call": {
"tool_name": "get_account_balance",
"parameters": {
"account_id": "ACC-12345"
}
}
}Load Testing
负载测试
Test agent capacity under high concurrency.
Configuration:
bash
undefined测试代理在高并发下的容量。
配置:
bash
undefinedSpawn 100 users, 1 per second, test for 10 minutes
生成100个用户,每秒1个,测试10分钟
elevenlabs test load
--users 100
--spawn-rate 1
--duration 600
--users 100
--spawn-rate 1
--duration 600
**Gotchas**:
- Load testing consumes real API credits
- Use burst pricing for expected traffic spikes
- Requires careful planning to avoid hitting rate limitselevenlabs test load
--users 100
--spawn-rate 1
--duration 600
--users 100
--spawn-rate 1
--duration 600
**注意事项**:
- 负载测试消耗真实API credits
- 预期流量峰值时使用峰值定价
- 需要精心规划以避免触发速率限制Simulation API (Programmatic Testing)
模拟API(程序化测试)
API Endpoint:
bash
POST /v1/convai/agents/:agent_id/simulateExample:
typescript
const simulation = await client.agents.simulate({
agent_id: 'agent_123',
scenario: 'Customer requests refund',
user_messages: [
"I want a refund for order #12345",
"I ordered it last week",
"Yes, please process it"
],
success_criteria: [
"Agent acknowledges request",
"Agent asks for order details",
"Agent provides refund timeline"
]
});
console.log('Test passed:', simulation.passed);
console.log('Criteria met:', simulation.evaluation.criteria_met);Use Cases:
- CI/CD integration (test before deploy)
- Regression testing
- Load testing preparation
API端点:
bash
POST /v1/convai/agents/:agent_id/simulate示例:
typescript
const simulation = await client.agents.simulate({
agent_id: 'agent_123',
scenario: 'Customer requests refund',
user_messages: [
"I want a refund for order #12345",
"I ordered it last week",
"Yes, please process it"
],
success_criteria: [
"Agent acknowledges request",
"Agent asks for order details",
"Agent provides refund timeline"
]
});
console.log('Test passed:', simulation.passed);
console.log('Criteria met:', simulation.evaluation.criteria_met);适用场景:
- CI/CD集成(部署前测试)
- 回归测试
- 负载测试准备
8. Analytics & Monitoring
8. 分析与监控
Conversation Analysis
对话分析
Extract structured data from conversation transcripts.
Features:
从对话转录本中提取结构化数据。
特性:
Success Evaluation (LLM-Based)
基于LLM的成功评估
json
{
"evaluation_criteria": {
"resolution": "Was the customer's issue resolved?",
"sentiment": "Was the conversation tone positive?",
"compliance": "Did the agent follow company policies?"
}
}json
{
"evaluation_criteria": {
"resolution": "Was the customer's issue resolved?",
"sentiment": "Was the conversation tone positive?",
"compliance": "Did the agent follow company policies?"
}
}Data Collection
数据收集
json
{
"data_collection": {
"fields": [
{ "name": "customer_name", "type": "string" },
{ "name": "issue_type", "type": "enum", "values": ["billing", "technical", "other"] },
{ "name": "satisfaction", "type": "number", "range": [1, 5] }
]
}
}Access:
- Via Post-call Webhooks (real-time)
- Via Analytics Dashboard (batch)
- Via API (on-demand)
json
{
"data_collection": {
"fields": [
{ "name": "customer_name", "type": "string" },
{ "name": "issue_type", "type": "enum", "values": ["billing", "technical", "other"] },
{ "name": "satisfaction", "type": "number", "range": [1, 5] }
]
}
}访问方式:
- 通过通话后Webhooks(实时)
- 通过分析仪表盘(批量)
- 通过API(按需)
Analytics Dashboard
分析仪表盘
Metrics:
- Resolution Rates: % of issues resolved
- CX Metrics: Sentiment, satisfaction, CSAT
- Compliance: Policy adherence, guardrail violations
- Performance: Response time, call duration, concurrency
- Tool Usage: Tool call frequency, success rates
- LLM Costs: Track costs per agent/conversation
Access: Dashboard → Analytics tab
指标:
- 解决率:问题解决的百分比
- CX指标:情感分析、满意度、CSAT
- 合规性:政策遵守情况、防护规则违规
- 性能:响应时间、通话时长、并发数
- 工具使用:工具调用频率、成功率
- LLM成本:按代理/对话跟踪成本
访问方式:仪表盘→分析标签页
9. Privacy & Compliance
9. 隐私与合规
Data Retention
数据保留
Default: 2 years (GDPR-compliant)
Configuration:
json
{
"privacy": {
"transcripts": {
"retention_days": 730 // 2 years (GDPR)
},
"audio": {
"retention_days": 2190 // 6 years (HIPAA)
}
}
}Compliance Recommendations:
- GDPR: Align with data processing purposes (typically 1-2 years)
- HIPAA: Minimum 6 years for medical records
- SOC 2: Encryption in transit and at rest (automatic)
默认:2年(符合GDPR)
配置:
json
{
"privacy": {
"transcripts": {
"retention_days": 730 // 2年(GDPR)
},
"audio": {
"retention_days": 2190 // 6年(HIPAA)
}
}
}合规建议:
- GDPR:与数据处理目的对齐(通常1-2年)
- HIPAA:医疗记录至少保留6年
- SOC 2:传输中与静态数据加密(自动)
Encryption
加密
- In Transit: TLS 1.3
- At Rest: AES-256
- Regional Compliance: Data residency (US, EU, India)
Regional Configuration:
typescript
const { startConversation } = useConversation({
serverLocation: 'eu-residency' // 'us' | 'global' | 'eu-residency' | 'in-residency'
});- 传输中:TLS 1.3
- 静态数据:AES-256
- 区域合规:数据驻留(美国、欧盟、印度)
区域配置:
typescript
const { startConversation } = useConversation({
serverLocation: 'eu-residency' // 'us' | 'global' | 'eu-residency' | 'in-residency'
});Zero Retention Mode
零保留模式
For maximum privacy, enable zero retention to immediately delete all conversation data.
Limitations:
- No conversation history
- No analytics
- No post-call webhooks
- No MCP tool integrations
为实现最大隐私,启用零保留模式可立即删除所有对话数据。
限制:
- 无对话历史
- 无分析
- 无通话后Webhooks
- 无MCP工具集成
10. Cost Optimization
10. 成本优化
LLM Caching
LLM缓存
Reduce costs by caching repeated inputs.
How It Works:
- First request: Full cost ()
input_cache_write - Subsequent requests: Reduced cost ()
input_cache_read - Automatic cache invalidation after TTL
Configuration:
json
{
"llm_config": {
"caching": {
"enabled": true,
"ttl_seconds": 3600 // 1 hour
}
}
}Use Cases:
- Repeated system prompts
- Large knowledge bases
- Frequent tool definitions
Savings: Up to 90% on cached inputs
通过缓存重复输入降低成本。
工作原理:
- 首次请求:全额成本()
input_cache_write - 后续请求:降低成本()
input_cache_read - 自动缓存失效:TTL后自动失效
配置:
json
{
"llm_config": {
"caching": {
"enabled": true,
"ttl_seconds": 3600 // 1小时
}
}
}适用场景:
- 重复的系统提示词
- 大型知识库
- 频繁的工具定义
节省成本:缓存输入最多可节省90%
Model Swapping
模型切换
Switch between models based on cost/performance needs.
Available Models:
- GPT-4o (high cost, high quality)
- GPT-4o-mini (medium cost, good quality)
- Claude Sonnet 4.5 (high cost, best reasoning)
- Gemini 2.5 Flash (low cost, fast)
Configuration:
json
{
"llm_config": {
"model": "gpt-4o-mini" // Swap anytime via dashboard or API
}
}根据成本/性能需求切换模型。
可用模型:
- GPT-4o(高成本,高质量)
- GPT-4o-mini(中等成本,良好质量)
- Claude Sonnet 4.5(高成本,最佳推理)
- Gemini 2.5 Flash(低成本,快速)
配置:
json
{
"llm_config": {
"model": "gpt-4o-mini" // 随时通过仪表盘或API切换
}
}Burst Pricing
峰值定价
Temporarily exceed concurrency limits during high-demand periods.
How It Works:
- Normal: Your subscription concurrency limit (e.g., 10 simultaneous calls)
- Burst: Up to 3x your limit (e.g., 30 simultaneous calls)
- Cost: 2x the standard rate for burst calls
Configuration:
json
{
"call_limits": {
"burst_pricing_enabled": true
}
}Use Cases:
- Black Friday traffic spikes
- Product launches
- Seasonal demand (holidays)
Gotchas:
- Burst calls cost 2x (plan accordingly)
- Not unlimited (3x cap)
高需求期间临时超出并发限制。
工作原理:
- 正常:订阅的并发限制(如10个同时通话)
- 峰值:最高可达限制的3倍(如30个同时通话)
- 成本:峰值通话按标准费率的2倍收费
配置:
json
{
"call_limits": {
"burst_pricing_enabled": true
}
}适用场景:
- 黑色星期五流量峰值
- 产品发布
- 季节性需求(节假日)
注意事项:
- 峰值通话成本为2倍(提前规划)
- 并非无限制(3倍上限)
11. Advanced Features
11. 高级特性
Events (WebSocket/SSE)
事件(WebSocket/SSE)
Real-time event streaming for live transcription, agent responses, and tool calls.
Event Types:
- - Audio stream chunks
audio - - Real-time transcription
transcript - - Agent's text response
agent_response - - Tool execution status
tool_call - - State updates
conversation_state
Example:
typescript
const { startConversation } = useConversation({
onEvent: (event) => {
switch (event.type) {
case 'transcript':
console.log('User said:', event.data.text);
break;
case 'agent_response':
console.log('Agent replied:', event.data.text);
break;
case 'tool_call':
console.log('Tool called:', event.data.tool_name);
break;
}
}
});实时事件流,用于实时转录、代理响应和工具调用。
事件类型:
- - 音频流片段
audio - - 实时转录
transcript - - 代理的文本响应
agent_response - - 工具执行状态
tool_call - - 状态更新
conversation_state
示例:
typescript
const { startConversation } = useConversation({
onEvent: (event) => {
switch (event.type) {
case 'transcript':
console.log('User said:', event.data.text);
break;
case 'agent_response':
console.log('Agent replied:', event.data.text);
break;
case 'tool_call':
console.log('Tool called:', event.data.tool_name);
break;
}
}
});Custom Models (Bring Your Own LLM)
自定义模型(自带LLM)
Use your own OpenAI API key or custom LLM server.
Configuration:
json
{
"llm_config": {
"custom": {
"endpoint": "https://api.openai.com/v1/chat/completions",
"api_key": "{{secret__openai_api_key}}",
"model": "gpt-4"
}
}
}Use Cases:
- Custom fine-tuned models
- Private LLM deployments (Ollama, LocalAI)
- Cost control (use your own credits)
- Compliance (on-premise models)
Gotchas:
- Endpoint must be OpenAI-compatible
- No official support for non-OpenAI-compatible models
使用自己的OpenAI API密钥或自定义LLM服务器。
配置:
json
{
"llm_config": {
"custom": {
"endpoint": "https://api.openai.com/v1/chat/completions",
"api_key": "{{secret__openai_api_key}}",
"model": "gpt-4"
}
}
}适用场景:
- 自定义微调模型
- 私有LLM部署(Ollama、LocalAI)
- 成本控制(使用自己的credits)
- 合规性(本地部署模型)
注意事项:
- 端点必须与OpenAI兼容
- 非OpenAI兼容模型无官方支持
Post-Call Webhooks
通话后Webhooks
Receive notifications when a call ends and analysis completes.
Configuration:
json
{
"webhooks": {
"post_call": {
"url": "https://api.example.com/webhook",
"headers": {
"Authorization": "Bearer {{secret__webhook_auth_token}}"
}
}
}
}Payload:
json
{
"conversation_id": "conv_123",
"agent_id": "agent_456",
"transcript": "...",
"duration_seconds": 120,
"analysis": {
"sentiment": "positive",
"resolution": true,
"extracted_data": {
"customer_name": "John Doe",
"issue_type": "billing"
}
}
}Security (HMAC Verification):
typescript
import crypto from 'crypto';
export async function POST(req: Request) {
const signature = req.headers.get('elevenlabs-signature');
const payload = await req.text();
const hmac = crypto
.createHmac('sha256', process.env.WEBHOOK_SECRET!)
.update(payload)
.digest('hex');
if (signature !== hmac) {
return new Response('Invalid signature', { status: 401 });
}
// Process webhook
const data = JSON.parse(payload);
console.log('Conversation ended:', data.conversation_id);
// MUST return 200
return new Response('OK', { status: 200 });
}Gotchas:
- Must return 200 status code
- Auto-disabled after 10 consecutive failures (7+ days since last success)
- Retry logic: 3 attempts with exponential backoff
通话结束且分析完成时接收通知。
配置:
json
{
"webhooks": {
"post_call": {
"url": "https://api.example.com/webhook",
"headers": {
"Authorization": "Bearer {{secret__webhook_auth_token}}"
}
}
}
}负载:
json
{
"conversation_id": "conv_123",
"agent_id": "agent_456",
"transcript": "...",
"duration_seconds": 120,
"analysis": {
"sentiment": "positive",
"resolution": true,
"extracted_data": {
"customer_name": "John Doe",
"issue_type": "billing"
}
}
}安全(HMAC验证):
typescript
import crypto from 'crypto';
export async function POST(req: Request) {
const signature = req.headers.get('elevenlabs-signature');
const payload = await req.text();
const hmac = crypto
.createHmac('sha256', process.env.WEBHOOK_SECRET!)
.update(payload)
.digest('hex');
if (signature !== hmac) {
return new Response('Invalid signature', { status: 401 });
}
// 处理Webhook
const data = JSON.parse(payload);
console.log('Conversation ended:', data.conversation_id);
// 必须返回200
return new Response('OK', { status: 200 });
}注意事项:
- 必须返回200状态码
- 连续10次失败后自动禁用(上次成功后7+天)
- 重试逻辑:3次尝试,指数退避
Chat Mode (Text-Only)
聊天模式(纯文本)
Disable voice, use text-only conversations.
Configuration:
json
{
"conversation_config": {
"chat_mode": true // Disables audio input/output
}
}Benefits:
- Faster response times (~200ms saved)
- Lower costs (no ASR/TTS charges)
- Easier testing (no microphone required)
Use Cases:
- Testing agents without audio
- Building text chat interfaces
- Accessibility (text-only users)
禁用语音,使用纯文本对话。
配置:
json
{
"conversation_config": {
"chat_mode": true // 禁用音频输入输出
}
}优势:
- 响应速度更快(节省约200ms)
- 成本更低(无ASR/TTS费用)
- 测试更简单(无需麦克风)
适用场景:
- 无需音频的代理测试
- 构建文本聊天界面
- 无障碍访问(纯文本用户)
Telephony Integration
电话系统集成
SIP Trunking:
SIP Endpoint: sip-static.rtc.elevenlabs.io
TLS Transport: Recommended for production
SRTP Encryption: SupportedSupported Providers: Twilio, Vonage, RingCentral, Sinch, Infobip, Telnyx, Exotel, Plivo, Bandwidth
Native Twilio Integration:
json
{
"telephony": {
"provider": "twilio",
"phone_number": "+1234567890",
"account_sid": "{{secret__twilio_account_sid}}",
"auth_token": "{{secret__twilio_auth_token}}"
}
}Use Cases:
- Customer support hotlines
- Appointment scheduling
- Order status inquiries
- IVR systems
SIP中继:
SIP端点: sip-static.rtc.elevenlabs.io
TLS传输: 生产环境推荐
SRTP加密: 支持支持的提供商:Twilio、Vonage、RingCentral、Sinch、Infobip、Telnyx、Exotel、Plivo、Bandwidth
原生Twilio集成:
json
{
"telephony": {
"provider": "twilio",
"phone_number": "+1234567890",
"account_sid": "{{secret__twilio_account_sid}}",
"auth_token": "{{secret__twilio_auth_token}}"
}
}适用场景:
- 客户支持热线
- 预约调度
- 订单状态查询
- IVR系统
12. CLI & DevOps ("Agents as Code")
12. CLI与DevOps(“代理即代码”)
Installation & Authentication
安装与认证
bash
undefinedbash
undefinedInstall globally
全局安装
npm install -g @elevenlabs/cli
npm install -g @elevenlabs/cli
Authenticate
认证
elevenlabs auth login
elevenlabs auth login
Set residency (for GDPR compliance)
设置数据驻留(GDPR合规)
elevenlabs auth residency eu-residency # or 'in-residency' | 'global'
elevenlabs auth residency eu-residency # 或 'in-residency' | 'global'
Check current user
检查当前用户
elevenlabs auth whoami
**Environment Variables** (For CI/CD):
```bash
export ELEVENLABS_API_KEY=your-api-keyelevenlabs auth whoami
**环境变量**(用于CI/CD):
```bash
export ELEVENLABS_API_KEY=your-api-keyProject Structure
项目结构
Initialize Project:
bash
elevenlabs agents initDirectory Structure Created:
your_project/
├── agents.json # Agent registry
├── tools.json # Tool configurations
├── tests.json # Test configurations
├── agent_configs/ # Individual agent files (.json)
├── tool_configs/ # Tool configuration files
└── test_configs/ # Test configuration files初始化项目:
bash
elevenlabs agents init生成的目录结构:
your_project/
├── agents.json # 代理注册表
├── tools.json # 工具配置
├── tests.json # 测试配置
├── agent_configs/ # 单个代理文件(.json)
├── tool_configs/ # 工具配置文件
└── test_configs/ # 测试配置文件Agent Management Commands
代理管理命令
bash
undefinedbash
undefinedCreate agent
创建代理
elevenlabs agents add "Support Agent" --template customer-service
elevenlabs agents add "Support Agent" --template customer-service
Deploy to platform
部署到平台
elevenlabs agents push
elevenlabs agents push --agent "Support Agent"
elevenlabs agents push --env prod
elevenlabs agents push --dry-run # Preview changes
elevenlabs agents push
elevenlabs agents push --agent "Support Agent"
elevenlabs agents push --env prod
elevenlabs agents push --dry-run # 预览更改
Import existing agents
导入现有代理
elevenlabs agents pull
elevenlabs agents pull
List agents
列出代理
elevenlabs agents list
elevenlabs agents list
Check sync status
检查同步状态
elevenlabs agents status
elevenlabs agents status
Delete agent
删除代理
elevenlabs agents delete <agent_id>
undefinedelevenlabs agents delete <agent_id>
undefinedTool Management Commands
工具管理命令
bash
undefinedbash
undefinedCreate webhook tool
创建Webhook工具
elevenlabs tools add-webhook "Get Weather" --config-path tool_configs/get-weather.json
elevenlabs tools add-webhook "Get Weather" --config-path tool_configs/get-weather.json
Create client tool
创建客户端工具
elevenlabs tools add-client "Update Cart" --config-path tool_configs/update-cart.json
elevenlabs tools add-client "Update Cart" --config-path tool_configs/update-cart.json
Deploy tools
部署工具
elevenlabs tools push
elevenlabs tools push
Import existing tools
导入现有工具
elevenlabs tools pull
elevenlabs tools pull
Delete tools
删除工具
elevenlabs tools delete <tool_id>
elevenlabs tools delete --all
undefinedelevenlabs tools delete <tool_id>
elevenlabs tools delete --all
undefinedTesting Commands
测试命令
bash
undefinedbash
undefinedCreate test
创建测试
elevenlabs tests add "Refund Test" --template basic-llm
elevenlabs tests add "Refund Test" --template basic-llm
Deploy tests
部署测试
elevenlabs tests push
elevenlabs tests push
Import tests
导入测试
elevenlabs tests pull
elevenlabs tests pull
Run test
运行测试
elevenlabs agents test "Support Agent"
undefinedelevenlabs agents test "Support Agent"
undefinedMulti-Environment Deployment
多环境部署
Pattern:
bash
undefined模式:
bash
undefinedDevelopment
开发环境
elevenlabs agents push --env dev
elevenlabs agents push --env dev
Staging
staging环境
elevenlabs agents push --env staging
elevenlabs agents push --env staging
Production (with confirmation)
生产环境(带确认)
elevenlabs agents push --env prod --dry-run
elevenlabs agents push --env prod --dry-run
Review changes...
查看更改...
elevenlabs agents push --env prod
**Environment-Specific Configs**:agent_configs/
├── support-bot.json # Base config
├── support-bot.dev.json # Dev overrides
├── support-bot.staging.json # Staging overrides
└── support-bot.prod.json # Prod overrides
undefinedelevenlabs agents push --env prod
**环境特定配置**:agent_configs/
├── support-bot.json # 基础配置
├── support-bot.dev.json # 开发环境覆盖
├── support-bot.staging.json # staging环境覆盖
└── support-bot.prod.json # 生产环境覆盖
undefinedCI/CD Integration
CI/CD集成
GitHub Actions Example:
yaml
name: Deploy Agent
on:
push:
branches: [main]
paths:
- 'agent_configs/**'
- 'tool_configs/**'
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Install CLI
run: npm install -g @elevenlabs/cli
- name: Test Configs
run: elevenlabs agents push --dry-run --env prod
env:
ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_PROD }}
- name: Deploy
run: elevenlabs agents push --env prod
env:
ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_PROD }}GitHub Actions示例:
yaml
name: Deploy Agent
on:
push:
branches: [main]
paths:
- 'agent_configs/**'
- 'tool_configs/**'
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Install CLI
run: npm install -g @elevenlabs/cli
- name: Test Configs
run: elevenlabs agents push --dry-run --env prod
env:
ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_PROD }}
- name: Deploy
run: elevenlabs agents push --env prod
env:
ELEVENLABS_API_KEY: ${{ secrets.ELEVENLABS_API_KEY_PROD }}Version Control Best Practices
版本控制最佳实践
Commit:
agent_configs/*.jsontool_configs/*.jsontest_configs/*.json- ,
agents.json,tools.jsontests.json
Ignore:
undefined提交:
agent_configs/*.jsontool_configs/*.jsontest_configs/*.json- ,
agents.json,tools.jsontests.json
忽略:
undefined.gitignore
.gitignore
.env
.elevenlabs/
*.secret.json
---.env
.elevenlabs/
*.secret.json
---13. Common Errors & Solutions
13. 常见错误与解决方案
Error 1: Missing Required Dynamic Variables
错误1:缺少必需的动态变量
Symptom: "Missing required dynamic variables" error, no transcript generated
Cause: Dynamic variables referenced in prompts/messages but not provided at conversation start
Solution:
typescript
const conversation = await client.conversations.create({
agent_id: "agent_123",
dynamic_variables: {
user_name: "John",
account_tier: "premium",
// Provide ALL variables referenced in prompts
}
});症状:“缺少必需的动态变量”错误,无转录本生成
原因:提示词/消息中引用了动态变量,但启动对话时未提供
解决方案:
typescript
const conversation = await client.conversations.create({
agent_id: "agent_123",
dynamic_variables: {
user_name: "John",
account_tier: "premium",
// 提供提示词中引用的所有变量
}
});Error 2: Case-Sensitive Tool Names
错误2:大小写敏感的工具名称
Symptom: Tool not executing, agent says "tool not found"
Cause: Tool name in config doesn't match registered name (case-sensitive)
Solution:
json
// agent_configs/bot.json
{
"agent": {
"prompt": {
"tool_ids": ["orderLookup"] // Must match exactly
}
}
}
// tool_configs/order-lookup.json
{
"name": "orderLookup" // Match case exactly
}症状:工具未执行,代理提示“工具未找到”
原因:配置中的工具名称与注册名称不匹配(大小写敏感)
解决方案:
json
// agent_configs/bot.json
{
"agent": {
"prompt": {
"tool_ids": ["orderLookup"] // 必须完全匹配
}
}
}
// tool_configs/order-lookup.json
{
"name": "orderLookup" // 完全匹配大小写
}Error 3: Webhook Authentication Failures
错误3:Webhook认证失败
Symptom: Webhook auto-disabled after failures
Cause:
- Incorrect HMAC signature verification
- Not returning 200 status code
- 10+ consecutive failures
Solution:
typescript
// Always verify HMAC signature
import crypto from 'crypto';
const signature = req.headers['elevenlabs-signature'];
const payload = JSON.stringify(req.body);
const hmac = crypto
.createHmac('sha256', process.env.WEBHOOK_SECRET)
.update(payload)
.digest('hex');
if (signature !== hmac) {
return res.status(401).json({ error: 'Invalid signature' });
}
// Process webhook
// ...
// MUST return 200
res.status(200).json({ success: true });症状:Webhook多次失败后自动禁用
原因:
- HMAC签名验证错误
- 未返回200状态码
- 连续10+次失败
解决方案:
typescript
// 始终验证HMAC签名
import crypto from 'crypto';
const signature = req.headers['elevenlabs-signature'];
const payload = JSON.stringify(req.body);
const hmac = crypto
.createHmac('sha256', process.env.WEBHOOK_SECRET)
.update(payload)
.digest('hex');
if (signature !== hmac) {
return res.status(401).json({ error: 'Invalid signature' });
}
// 处理Webhook
// ...
// 必须返回200
res.status(200).json({ success: true });Error 4: Voice Consistency Issues
错误4:语音一致性问题
Symptom: Generated audio varies in volume/tone
Cause:
- Background noise in voice clone training data
- Inconsistent microphone distance
- Whispering or shouting in samples
Solution:
- Use clean audio samples (no music, noise, pops)
- Maintain consistent microphone distance
- Avoid extreme volumes
- Test voice settings before deployment
症状:生成的音频音量/语调不一致
原因:
- 语音克隆训练数据中有背景噪音
- 麦克风距离不一致
- 样本中有低语或大喊
解决方案:
- 使用清晰的音频样本(无音乐、噪音、爆音)
- 保持麦克风距离一致
- 避免极端音量
- 部署前测试语音设置
Error 5: Wrong Language Voice
错误5:语言与语音不匹配
Symptom: Unpredictable pronunciation, accent issues
Cause: Using English-trained voice for non-English language
Solution:
json
{
"language_presets": [
{
"language": "es",
"voice_id": "spanish_trained_voice_id" // Must be Spanish-trained
}
]
}症状:发音不可预测,口音问题
原因:将英语训练的语音用于非英语语言
解决方案:
json
{
"language_presets": [
{
"language": "es",
"voice_id": "spanish_trained_voice_id" // 必须是西班牙语训练的语音
}
]
}Error 6: Restricted API Keys Not Supported (CLI)
错误6:CLI不支持受限API密钥
Symptom: CLI authentication fails
Cause: Using restricted API key (not currently supported)
Solution: Use unrestricted API key for CLI operations
症状:CLI认证失败
原因:使用了受限API密钥(目前不支持)
解决方案:使用无限制API密钥进行CLI操作
Error 7: Agent Configuration Push Conflicts
错误7:代理配置推送冲突
Symptom: Changes not reflected after push
Cause: Hash-based change detection missed modification
Solution:
bash
undefined症状:推送后更改未生效
原因:基于哈希的变更检测未检测到修改
解决方案:
bash
undefinedForce re-sync
强制重新同步
elevenlabs agents init --override
elevenlabs agents pull # Re-import from platform
elevenlabs agents init --override
elevenlabs agents pull # 从平台重新导入
Make changes
进行更改
elevenlabs agents push
undefinedelevenlabs agents push
undefinedError 8: Tool Parameter Schema Mismatch
错误8:工具参数架构不匹配
Symptom: Tool called but parameters empty or incorrect
Cause: Schema definition doesn't match actual usage
Solution:
json
// tool_configs/order-lookup.json
{
"parameters": {
"type": "object",
"properties": {
"order_id": {
"type": "string",
"description": "The order ID to look up (format: ORD-12345)" // Clear description
}
},
"required": ["order_id"]
}
}症状:工具被调用但参数为空或错误
原因:架构定义与实际使用不匹配
解决方案:
json
// tool_configs/order-lookup.json
{
"parameters": {
"type": "object",
"properties": {
"order_id": {
"type": "string",
"description": "The order ID to look up (format: ORD-12345)" // 清晰的描述
}
},
"required": ["order_id"]
}
}Error 9: RAG Index Not Ready
错误9:RAG索引未就绪
Symptom: Agent doesn't use knowledge base
Cause: RAG index still computing (can take minutes for large documents)
Solution:
typescript
// Check index status before using
const index = await client.knowledgeBase.getRagIndex({
document_id: 'doc_123'
});
if (index.status !== 'ready') {
console.log('Index still computing...');
}症状:代理未使用知识库
原因:RAG索引仍在计算中(大型文档可能需要数分钟)
解决方案:
typescript
// 使用前检查索引状态
const index = await client.knowledgeBase.getRagIndex({
document_id: 'doc_123'
});
if (index.status !== 'ready') {
console.log('Index still computing...');
}Error 10: WebSocket Protocol Error (1002)
错误10:WebSocket协议错误(1002)
Symptom: Intermittent "protocol error" when using WebSocket connections
Cause: Network instability or incompatible browser
Solution:
- Use WebRTC instead of WebSocket (more resilient)
- Implement reconnection logic
- Check browser compatibility
症状:使用WebSocket连接时间歇性出现“协议错误”
原因:网络不稳定或浏览器不兼容
解决方案:
- 使用WebRTC替代WebSocket(更具弹性)
- 实现重连逻辑
- 检查浏览器兼容性
Error 11: 401 Unauthorized in Production
错误11:生产环境401未授权
Symptom: Works locally but fails in production
Cause: Agent visibility settings or API key configuration
Solution:
- Check agent visibility (public vs private)
- Verify API key is set in production environment
- Check allowlist configuration if enabled
症状:本地正常但生产环境失败
原因:代理可见性设置或API密钥配置错误
解决方案:
- 检查代理可见性(公共vs私有)
- 验证生产环境中API密钥已设置
- 若启用了白名单,检查白名单配置
Error 12: Allowlist Connection Errors
错误12:白名单连接错误
Symptom: "Host elevenlabs.io is not allowed to connect to this agent"
Cause: Agent has allowlist enabled but using shared link
Solution:
- Configure agent allowlist with correct domains
- Or disable allowlist for testing
症状:“Host elevenlabs.io is not allowed to connect to this agent”
原因:代理启用了白名单,但使用了共享链接
解决方案:
- 配置代理白名单,添加正确的域名
- 或为测试禁用白名单
Error 13: Workflow Infinite Loops
错误13:工作流无限循环
Symptom: Agent gets stuck in workflow, never completes
Cause: Edge conditions creating loops
Solution:
- Add max iteration limits
- Test all edge paths
- Add explicit exit conditions
症状:代理陷入工作流,无法完成
原因:边缘条件导致循环
解决方案:
- 添加最大迭代限制
- 测试所有边缘路径
- 添加明确的退出条件
Error 14: Burst Pricing Not Enabled
错误14:未启用峰值定价
Symptom: Calls rejected during traffic spikes
Cause: Burst pricing not enabled in agent settings
Solution:
json
{
"call_limits": {
"burst_pricing_enabled": true
}
}症状:流量峰值时通话被拒绝
原因:代理设置中未启用峰值定价
解决方案:
json
{
"call_limits": {
"burst_pricing_enabled": true
}
}Error 15: MCP Server Timeout
错误15:MCP服务器超时
Symptom: MCP tools not responding
Cause: MCP server slow or unreachable
Solution:
- Check MCP server URL is accessible
- Verify transport type (SSE vs HTTP)
- Check authentication token
- Monitor MCP server logs
症状:MCP工具无响应
原因:MCP服务器缓慢或不可达
解决方案:
- 检查MCP服务器URL是否可访问
- 验证传输类型(SSE vs HTTP)
- 检查认证令牌
- 监控MCP服务器日志
Error 16: First Message Cutoff on Android
错误16:Android设备首条消息截断
Symptom: First message from agent gets cut off on Android devices (works fine on iOS/web)
Cause: Android devices need time to switch to correct audio mode after connection
Solution:
typescript
import { useConversation } from '@elevenlabs/react';
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// Add connection delay for Android
connectionDelay: {
android: 3_000, // 3 seconds (default)
ios: 0, // No delay needed
default: 0 // Other platforms
},
// Rest of config...
});Explanation:
- Android needs 3 seconds to switch audio routing mode
- Without delay, first audio chunk is lost
- iOS and web don't have this issue
- Adjust delay if 3 seconds isn't sufficient
Testing:
bash
undefined症状:Android设备上代理的首条消息被截断(iOS/Web正常)
原因:Android设备连接后需要时间切换到正确的音频模式
解决方案:
typescript
import { useConversation } from '@elevenlabs/react';
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// 为Android添加连接延迟
connectionDelay: {
android: 3_000, // 3秒(默认)
ios: 0, // 无需延迟
default: 0 // 其他平台
},
// 其余配置...
});说明:
- Android需要3秒切换音频路由模式
- 无延迟的话,首段音频会丢失
- iOS和Web无此问题
- 若3秒不够,可调整延迟
测试:
bash
undefinedTest on Android device
在Android设备上测试
npm run android
npm run android
First message should now be complete
首条消息现在应该完整
undefinedundefinedError 17: CSP (Content Security Policy) Violations
错误17:CSP(内容安全策略)违规
Symptom: "Refused to load the script because it violates the following Content Security Policy directive" errors in browser console
Cause: Applications with strict Content Security Policy don't allow or URLs in directive. ElevenLabs SDK uses Audio Worklets that are loaded as blobs by default.
data:blob:script-srcSolution - Self-Host Worklet Files:
Step 1: Copy worklet files to your public directory:
bash
undefined症状:浏览器控制台出现“Refused to load the script because it violates the following Content Security Policy directive”错误
原因:具有严格内容安全策略的应用不允许或URL在指令中。ElevenLabs SDK默认使用Blob加载Audio Worklets。
data:blob:script-src解决方案 - 自托管Worklet文件:
步骤1:将Worklet文件复制到公共目录:
bash
undefinedCopy from node_modules
从node_modules复制
cp node_modules/@elevenlabs/client/dist/worklets/*.js public/elevenlabs/
**Step 2**: Configure SDK to use self-hosted worklets:
```typescript
import { useConversation } from '@elevenlabs/react';
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// Point to self-hosted worklet files
workletPaths: {
'rawAudioProcessor': '/elevenlabs/rawAudioProcessor.worklet.js',
'audioConcatProcessor': '/elevenlabs/audioConcatProcessor.worklet.js',
},
// Rest of config...
});Step 3: Update CSP headers to allow self-hosted scripts:
nginx
undefinedcp node_modules/@elevenlabs/client/dist/worklets/*.js public/elevenlabs/
**步骤2**:配置SDK使用自托管的Worklet文件:
```typescript
import { useConversation } from '@elevenlabs/react';
const { startConversation } = useConversation({
agentId: 'your-agent-id',
// 指向自托管的Worklet文件
workletPaths: {
'rawAudioProcessor': '/elevenlabs/rawAudioProcessor.worklet.js',
'audioConcatProcessor': '/elevenlabs/audioConcatProcessor.worklet.js',
},
// 其余配置...
});步骤3:更新CSP头以允许自托管脚本:
nginx
undefinednginx example
nginx示例
add_header Content-Security-Policy "
default-src 'self';
script-src 'self' https://elevenlabs.io;
connect-src 'self' https://api.elevenlabs.io wss://api.elevenlabs.io;
worker-src 'self';
" always;
**Worklet Files Location**:node_modules/@elevenlabs/client/dist/worklets/
├── rawAudioProcessor.worklet.js
└── audioConcatProcessor.worklet.js
**Gotchas**:
- Worklet files must be served from same origin (CORS restriction)
- Update worklet files when upgrading `@elevenlabs/client`
- Paths must match exactly (case-sensitive)
**When You Need This**:
- Enterprise applications with strict CSP
- Government/financial apps
- Apps with security audits
- Any app blocking `blob:` URLs
---add_header Content-Security-Policy "
default-src 'self';
script-src 'self' https://elevenlabs.io;
connect-src 'self' https://api.elevenlabs.io wss://api.elevenlabs.io;
worker-src 'self';
" always;
**Worklet文件位置**:node_modules/@elevenlabs/client/dist/worklets/
├── rawAudioProcessor.worklet.js
└── audioConcatProcessor.worklet.js
**注意事项**:
- Worklet文件必须从同一源提供(CORS限制)
- 升级`@elevenlabs/client`时更新Worklet文件
- 路径必须完全匹配(大小写敏感)
**何时需要此方案**:
- 具有严格CSP的企业应用
- 政府/金融应用
- 经过安全审计的应用
- 任何阻止`blob:`URL的应用
---Integration with Existing Skills
与现有技能集成
This skill composes well with:
- cloudflare-worker-base → Deploy agents on Cloudflare Workers edge network
- cloudflare-workers-ai → Use Cloudflare LLMs as custom models in agents
- cloudflare-durable-objects → Persistent conversation state and session management
- cloudflare-kv → Cache agent configurations and user preferences
- nextjs → React SDK integration in Next.js applications
- ai-sdk-core → Vercel AI SDK provider for unified AI interface
- clerk-auth → Authenticated voice sessions with user identity
- hono-routing → API routes for webhooks and server tools
本技能可与以下技能良好集成:
- cloudflare-worker-base → 在Cloudflare Workers边缘网络部署代理
- cloudflare-workers-ai → 使用Cloudflare LLMs作为代理中的自定义模型
- cloudflare-durable-objects → 持久化对话状态和会话管理
- cloudflare-kv → 缓存代理配置和用户偏好
- nextjs → 在Next.js应用中集成React SDK
- ai-sdk-core → Vercel AI SDK提供统一AI接口
- clerk-auth → 带用户身份的认证语音会话
- hono-routing → Webhook和服务器工具的API路由
Additional Resources
其他资源
Official Documentation:
- Platform Overview: https://elevenlabs.io/docs/agents-platform/overview
- API Reference: https://elevenlabs.io/docs/api-reference
- CLI GitHub: https://github.com/elevenlabs/cli
Examples:
- Official Examples: https://github.com/elevenlabs/elevenlabs-examples
- MCP Server: https://github.com/elevenlabs/elevenlabs-mcp
Community:
- Discord: https://discord.com/invite/elevenlabs
- Twitter: @elevenlabsio
Production Tested: WordPress Auditor, Customer Support Agents
Last Updated: 2025-11-03
Package Versions: elevenlabs@1.59.0, @elevenlabs/cli@0.2.0
官方文档:
- 平台概述:https://elevenlabs.io/docs/agents-platform/overview
- API参考:https://elevenlabs.io/docs/api-reference
- CLI GitHub:https://github.com/elevenlabs/cli
示例:
- 官方示例:https://github.com/elevenlabs/elevenlabs-examples
- MCP服务器:https://github.com/elevenlabs/elevenlabs-mcp
社区:
- Discord:https://discord.com/invite/elevenlabs
- Twitter:@elevenlabsio
生产环境测试:WordPress审核员、客户支持代理
最后更新:2025-11-03
包版本:elevenlabs@1.59.0, @elevenlabs/cli@0.2.0