Language

This guide shows you how to configure your agent to speak multiple languages. You'll learn to:

• Configure your agent's primary language
• Add support for multiple languages
• Set language-specific voices and first messages
• Optimize voice selection for natural pronunciation
• Enable automatic language switching

Manage agents from your AI assistant

You can also make these changes conversationally. The hosted MCP server lets Claude and other MCP clients create, configure, and manage your agents through natural language.

When you create a new agent, it's configured with:

• English as the primary language
• Flash v2 model for fast, English-only responses
• A default first message.

Navigate to your agent's configuration page and locate the Agent tab.

1. In the Additional Languages add an additional language (e.g. French)
2. Review the first message, which is automatically translated using a Large Language Model (LLM). Customize it as needed for each additional language to ensure accuracy and cultural relevance.

elevenlabs agents pull --agent "<agent-name>"

Set conversation_config.agent.language for the primary language and add entries to conversation_config.language_presets for each additional language. Each preset can override the first message and other conversation config fields per language:

{
  "conversation_config": {
    "agent": {
      "language": "en"
    },
    "language_presets": {
      "fr": {
        "overrides": {
          "agent": {
            "first_message": "Bonjour, comment puis-je vous aider ?"
          }
        }
      }
    }
  }
}

elevenlabs agents push --agent "<agent-name>"

from elevenlabs import ElevenLabs

elevenlabs = ElevenLabs()

elevenlabs.conversational_ai.agents.update(
    agent_id="agent_7101k5zvyjhmfg983brhmhkd98n6",
    conversation_config={
        "agent": {"language": "en"},
        "language_presets": {
            "fr": {
                "overrides": {
                    "agent": {"first_message": "Bonjour, comment puis-je vous aider ?"},
                },
            },
        },
    },
)

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";

const elevenlabs = new ElevenLabsClient();

await elevenlabs.conversationalAi.agents.update("agent_7101k5zvyjhmfg983brhmhkd98n6", {
  conversationConfig: {
    agent: { language: "en" },
    languagePresets: {
      fr: {
        overrides: {
          agent: { firstMessage: "Bonjour, comment puis-je vous aider ?" },
        },
      },
    },
  },
});

For optimal pronunciation, configure each additional language with a language-specific voice from our Voice Library.

Add the language detection tool to your agent can automatically switch to the user's preferred language.

Now that the agent is configured to support additional languages, the widget will prompt the user for their preferred language before the conversation begins.

If using the SDK, the language can be set programmatically using conversation overrides. See the Overrides guide for implementation details.

You can integrate the widget with your internationalization framework by dynamically setting the language and UI text attributes.

Widget

<elevenlabs-convai
  language="es"
  action-text={i18n["es"]["actionText"]}
  start-call-text={i18n["es"]["startCall"]}
  end-call-text={i18n["es"]["endCall"]}
  expand-text={i18n["es"]["expand"]}
  listening-text={i18n["es"]["listening"]}
  speaking-text={i18n["es"]["speaking"]}
></elevenlabs-convai>

Select voices specifically trained in your target languages. This ensures:

• Natural pronunciation
• Appropriate regional accents
• Better handling of language-specific nuances

While automatic translations are provided, consider:

• Reviewing translations for accuracy
• Adapting greetings for cultural context
• Adjusting formal/informal tone as needed