Skip to main content
POST
https://app.famulor.de/api/
/
user
/
assistant
Create assistant
curl --request POST \
  --url https://app.famulor.de/api/user/assistant \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "assistant_name": "<string>",
  "voice_id": 123,
  "language": "<string>",
  "llm_model": "<string>",
  "calls_direction": "<string>",
  "engine_type": "<string>",
  "timezone": "<string>",
  "initial_message": "<string>",
  "system_prompt": "<string>",
  "phone_number_id": 123,
  "tool_ids": [
    123
  ],
  "endpoint_type": "<string>",
  "endpoint_sensitivity": 123,
  "interrupt_sensitivity": 123,
  "ambient_sound_volume": 123,
  "post_call_evaluation": true,
  "send_webhook_only_on_completed": true,
  "include_recording_in_webhook": true,
  "is_webhook_active": true,
  "webhook_url": "<string>",
  "use_min_interrupt_words": true,
  "min_interrupt_words": 123,
  "variables": {},
  "post_call_schema": [
    {
      "post_call_schema[].name": "<string>",
      "post_call_schema[].type": "<string>",
      "post_call_schema[].description": "<string>"
    }
  ],
  "end_call_tool.description": "<string>",
  "llm_temperature": 123,
  "voice_stability": 123,
  "voice_similarity": 123,
  "speech_speed": 123,
  "allow_interruptions": true,
  "filler_audios": true,
  "re_engagement_interval": 123,
  "max_call_duration": 123,
  "max_silence_duration": 123,
  "end_call_on_voicemail": true,
  "noise_cancellation": true,
  "record_call": true,
  "who_speaks_first": "<string>"
}
'
{
  "message": "Assistant created successfully",
  "data": {
    "id": 789,
    "name": "Sales Assistant",
    "status": "active",
    "type": "outbound",
    "mode": "pipeline"
  }
}
Create a new AI assistant with full configuration options. You can customize voice, language, behavior, and many other settings.

​
Request Body

​
Required Fields

​
assistant_name
string
required
Assistant display name (maximum 255 characters)
​
voice_id
integer
required
Voice identifier to use (must exist in available voices list)
​
language
string
required
Language name for the assistant (maximum 100 characters)
​
llm_model
string
required
Large Language Model name to use (maximum 100 characters)
​
calls_direction
string
required
Call direction configuration. Valid options: receive, make
​
engine_type
string
required
Engine type selection. Valid options: pipeline, multimodal
​
timezone
string
required
Timezone setting (example: “America/New_York”)
​
initial_message
string
required
Opening message the assistant will speak at call start
​
system_prompt
string
required
System prompt that defines the assistant’s behavior, personality, and instructions

​
Optional Configuration

​
phone_number_id
integer
Phone number identifier to assign (must exist in your phone numbers)
​
tool_ids
integer[]
Array of mid-call tool identifiers to attach. Each ID must be a valid tool belonging to your account.
​
endpoint_type
string
Voice activity detection method. Options: vad, ai
​
endpoint_sensitivity
number
Endpoint sensitivity level (range: 0-5)
​
interrupt_sensitivity
number
Interruption sensitivity level (range: 0-5)
​
ambient_sound_volume
number
Ambient sound volume level (range: 0-1)
​
post_call_evaluation
boolean
Enable AI-powered call evaluation after call completion
​
send_webhook_only_on_completed
boolean
Send webhooks only for successfully completed calls
​
include_recording_in_webhook
boolean
Include call recording URL in webhook payload

​
Webhook Configuration

​
is_webhook_active
boolean
Enable webhook notifications
​
webhook_url
string
Webhook endpoint URL for post-call notifications (required if is_webhook_active is true)

​
Interruption Settings

​
use_min_interrupt_words
boolean
Enable minimum interrupt words configuration
​
min_interrupt_words
integer
Minimum words required before interruption is allowed (range: 0-10)

​
Variables and Schema

​
variables
object
Custom key-value variable pairs for the assistant
​
post_call_schema
array
Schema definition for AI data extraction after calls

​
End Call Tool

​
end_call_tool.description
string
Description for end call tool functionality (maximum 500 characters)

​
Voice and Speech Settings

​
llm_temperature
number
LLM temperature configuration (range: 0-1)
​
voice_stability
number
Voice stability configuration (range: 0-1)
​
voice_similarity
number
Voice similarity configuration (range: 0-1)
​
speech_speed
number
Speech speed multiplier (range: 0.7-1.2)

​
Call Behavior Settings

​
allow_interruptions
boolean
Allow customers to interrupt the assistant
​
filler_audios
boolean
Use filler audio responses during processing
​
re_engagement_interval
integer
Re-engagement interval in seconds (range: 7-600)
​
max_call_duration
integer
Maximum call length in seconds (range: 20-1200)
​
max_silence_duration
integer
Maximum silence duration before re-engagement in seconds (range: 1-120)
​
end_call_on_voicemail
boolean
Automatically end call when voicemail is detected
​
noise_cancellation
boolean
Enable noise cancellation during calls
​
record_call
boolean
Record the call audio
​
who_speaks_first
string
Party that speaks first. Options: AI assistant, Customer

​
Response

​
message
string
Success confirmation message
​
data
object

​
Error Responses

​
422 Validation Error
​
500 Internal Server Error
{
  "message": "Assistant created successfully",
  "data": {
    "id": 789,
    "name": "Sales Assistant",
    "status": "active",
    "type": "outbound",
    "mode": "pipeline"
  }
}

​
Notes

  • All required fields must be provided to successfully create an assistant
  • Optional fields not specified will use default system values
  • Phone number assignment is optional, but if provided, the number must belong to your account
  • Webhook URL is mandatory when is_webhook_active is set to true
  • Voice and language identifiers must match available options from the system