Assistants

Create assistant

Create a new AI assistant with specified configuration

This endpoint allows you to create a new AI assistant with comprehensive configuration options.

Request Body

Core Required Fields

assistant_name string required

The name of the assistant (max 255 characters)

voice_id integer required

The voice ID to use for the assistant (must exist in available voices)

language string required

The language name for the assistant (max 100 characters)

llm_model string required

The LLM model name to use (max 100 characters)

calls_direction string required

The call direction type. Options: receive, make

engine_type string required

The engine type to use. Options: pipeline, multimodal

timezone string required

The timezone for the assistant (e.g., “America/New_York”)

initial_message string required

The initial message the assistant will speak when the call starts

system_prompt string required

The system prompt that defines the assistant’s behavior and personality

Optional Configuration

phone_number_id integer

The ID of a phone number to assign to the assistant (must exist in user’s phone numbers)

endpoint_type string

Voice activity detection type. Options: vad, ai

endpoint_sensitivity number

Endpoint sensitivity level (0-5)

interrupt_sensitivity number

Interrupt sensitivity level (0-5)

ambient_sound_volume number

Ambient sound volume level (0-1)

post_call_evaluation boolean

Whether to enable post-call evaluation

send_webhook_only_on_completed boolean

Whether to send webhooks only on completed calls

include_recording_in_webhook boolean

Whether to include recording URL in webhook payload

Webhook Configuration

is_webhook_active boolean

Whether webhook notifications are enabled

webhook_url string

The webhook URL for post-call notifications (required if is_webhook_active is true)

Interruption Settings

use_min_interrupt_words boolean

Whether to use minimum interrupt words setting

min_interrupt_words integer

Minimum number of words before interruption is allowed (0-10)

Variables and Schema

variables object

Key-value pairs of custom variables for the assistant

post_call_schema array

Schema definition for post-call data extraction

post_call_schema[].name string required

post_call_schema[].type string required

post_call_schema[].description string required

End Call Tool

end_call_tool.description string

Description for the end call tool functionality (max 500 characters)

Voice and Speech Settings

llm_temperature number

LLM temperature setting (0-1)

voice_stability number

Voice stability setting (0-1)

voice_similarity number

Voice similarity setting (0-1)

speech_speed number

Speech speed multiplier (0.7-1.2)

Call Behavior Settings

allow_interruptions boolean

Whether to allow caller interruptions

filler_audios boolean

Whether to use filler audio during processing

re_engagement_interval integer

Re-engagement interval in seconds (7-600)

max_call_duration integer

Maximum call duration in seconds (20-1200)

max_silence_duration integer

Maximum silence duration in seconds (1-120)

end_call_on_voicemail boolean

Whether to end call when voicemail is detected

noise_cancellation boolean

Whether to enable noise cancellation

record_call boolean

Whether to record the call

who_speaks_first string

Who speaks first in the call. Options: AI assistant, Customer

Response

message string

Success message confirming assistant creation

data object

id integer

name string

status string

type string

mode string

Error Responses

422 Validation Error

message string

errors object

500 Internal Server Error

message string

Notes

• All required fields must be provided for successful assistant creation
• The assistant will be created with default settings for any optional fields not specified
• Phone number assignment is optional but the phone number must belong to the authenticated user
• Webhook URL is required only when is_webhook_active is set to true
• Voice and language identifiers must correspond to available options in the system