Configure

Voice customization

Learn how to customize your AI agent's voice and speech patterns.

Overview

You can customize various aspects of your AI agent’s voice to create a more natural and engaging conversation experience. This includes controlling pronunciation, speaking speed, and language-specific voice settings.

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.

Available customizations

Multi-voice support

Enable your agent to switch between different voices for multi-character conversations, storytelling, and language tutoring.

Pronunciation dictionary

Control how your agent pronounces specific words and phrases using IPA or CMU notation.

Speed control

Adjust how quickly or slowly your agent speaks, with values ranging from 0.7x to 1.2x.

Expressive mode

Context-aware emotional delivery powered by Eleven v3 Conversational and an improved turn-taking system.

Audio environment

Add a looping background sound and apply a phone-style filter to outbound agent audio.

Language-specific voices

Configure different voices for each supported language to ensure natural pronunciation.

Best practices

Voices with live moderation enabled cannot be used in ElevenAgents.

Choose voices that match your target language and region for the most natural pronunciation. Consider testing multiple voices to find the best fit for your use case.

Start with the default speed (1.0) and adjust based on your specific needs. Test different speeds with your content to find the optimal balance between clarity and natural flow.

Focus on terms specific to your business or use case that need consistent pronunciation and are not widely used in everyday conversation. Test pronunciations with your chosen voice and model combination.

Some voice customization features may be model-dependent. For example, phoneme-based pronunciation control is only available with the Flash v2 model.