Skip to main content
Follow these steps to configure the fundamental settings for your agent, optimizing it for your specific business requirements.
1

Select a Language Model

We recommend starting with GPT-4.1, which offers an optimal balance of:
  • Response quality
  • Latency
  • Cost-effectiveness
LLM model selector showing GPT-4.1-mini and other available models
2

Select a Voice

Choose from available voices, each with a unique voice ID. Preview voices before selecting to find the right fit for your use case.Use the Voice Speed slider (0.5x – 2.0x) to control how fast your agent speaks. You can set a fixed speed or enable dynamic adaptation so the agent adjusts based on how fast the caller speaks.
Voice settings panel showing ElevenLabs voice models, speed, temperature, and volume controls
3

Set Conversation Initiation

Choose how your agent starts each call:
ModeBehavior
Wait for userAgent stays silent until the caller speaks first
Agent speaks firstAgent opens with a preset message or guided opening
Conversation Start setting with custom greeting text field

​
More Settings

After the core setup, configure these additional areas to fine-tune your agent.

Global Prompt

Define your agent’s persona, identity, and behavioral guardrails that apply across all states.

Knowledge Base

Supply contextual documents, URLs, and text your agent can reference during calls.

Speech Settings

Fine-tune responsiveness, interruption sensitivity, backchanneling, pronunciation, and keyword recognition.

Call Settings

Configure voicemail detection, silence-based call termination, maximum call duration, and initial pause timing.

Post-Call Analysis

Set up call review features to analyze performance after each conversation.

Privacy & Webhook

Manage data storage preferences and configure webhook event notifications.

​
Next Steps

Once basic settings are configured, move on to adding function calling to give your agent the ability to take actions during calls.