Agents
Create Agent
POST
Create a new AI voice agent with specific configuration for STT, TTS, LLM, and behavior.
Headers
string
required
Your API key for authentication.
string
required
The organization ID.
string
required
Must be
application/json.Permissions
agents:create(admin, agent_manager)
Request Body
string
required
The name of the agent (1-100 characters).
string
required
Speech-to-Text provider (e.g.,
deepgram, deepgram-nova-3, aws).string
required
Text-to-Speech provider (e.g.,
elevenlabs, cartesia, deepgram).string
required
Voice ID for the selected TTS provider.
string
required
LLM provider (e.g.,
openai, anthropic, google).string
required
Model ID (e.g.,
gpt-4o, gemini-2.5-flash-lite).string
required
The system prompt that defines the agent’s persona and instructions (10-10000 characters).
string
default:"EN"
Primary language for the agent (e.g.,
EN, ES).boolean
default:"false"
Whether the agent should speak first when the call connects.
boolean
default:"false"
Enable the built-in end call tool for the agent.
number
default:"0.7"
Temperature setting for the LLM (0.0 to 2.0).
string
Fallback LLM provider when primary fails.
string
Fallback LLM model when primary fails.
boolean
default:"false"
Enable call recording for this agent.
boolean
default:"false"
Enable AMD (Answering Machine Detection).
string
Message to leave if a voicemail is detected.
number
default:"2.0"
Delay in seconds before speaking the voicemail message (1.0-5.0).
array
List of custom tool IDs to attach to this agent.
array
List of knowledge base document IDs to attach to this agent.
array
List of phone number IDs to assign to this agent.
Response
boolean
Indicates if the request was successful.
string
Human-readable success message.
object
The created agent object (AgentData).