Assistants

Update assistant

Update an existing AI assistant’s configuration

This endpoint allows you to update an existing AI assistant’s configuration. All fields are optional - only provide the fields you want to update.

Path Parameters

id integer required

The unique identifier of the assistant to update

Request Body

Core Fields

assistant_name string

The name of the assistant (max 255 characters)

voice_id integer

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

languagestring

The language name for the assistant (max 100 characters)

llm_model string

The LLM model name to use (max 100 characters)

calls_direction string

The call direction type. Options: receive, make

engine_type string

The engine type to use. Options: pipeline, multimodal

timezone string

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

initial_message string

The initial message the assistant will speak when the call starts

system_prompt string

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 (set to null to unassign)

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 (can be set to null to remove)

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 update

data object

id integer

name string

status string

type string

mode string

Error Responses

404 Not Found

message string

422 Validation Error

message string

errors object

500 Internal Server Error

message string

Notes

• Only the fields you provide in the request body will be updated
• All validation rules apply the same as when creating an assistant
• To remove a phone number assignment, set phone_number_id to null
• To disable webhook, set webhook_url to null or is_webhook_active to false
• The assistant must belong to the authenticated user to be updated