​

Agent: Building an Intelligent Voice Experience

​

Basic Settings

• Agent Name
  Give your agent a recognizable name.
• Voice Type
  Select the voice gender (male or female) for the agent’s tone.
• Agent Description
  Add a short internal description to help identify this agent’s purpose or use case.
• Voicemail Message
  Define what the agent should say if it reaches voicemail.
• Predefined Prompt
  Choose from saved prompts in your Prompt Library.
• Custom Prompt
  Alternatively, add or edit a custom prompt directly.

​

Advanced Settings

• Select a Voice
  Choose a specific voice from your created voice assets.
• Model Language
  Define the language your agent will operate in.
• LLM Provider
  Select your preferred large language model provider (e.g., OpenAI).
• Model Name
  Choose from available models:
  • GPT-4
  • GPT-4 Turbo
  • GPT-4 Omni
  • GPT-4 Omni Mini
  • GPT-3.5
  • GPT-3.5 Turbo
  Note: Latency and performance may vary by model.
• Speech-to-Text Provider
  Select the provider that transcribes incoming speech.
• Webhooks
  Add one or more webhooks to send real-time data from the conversation.
• Actions
  Assign specific actions the agent can perform (e.g., send SMS, update lead).
• LLM Temperature
  Set how creative or deterministic the agent’s responses should be (higher = more creative).
• Conversation Speed
  Control agent interruptions:
  • Lower values = slower to interrupt
  • Higher values = faster to respond, may speak over user
• Max Idle Check Count
  Maximum number of times the agent will ask if the user is still there before ending the call.
• Idle Time (seconds)
  Time the agent waits before checking if the person is still on the line.
• Call Duration (seconds)
  Maximum total time the agent is allowed to stay on the call.