Skip to main content
POST
/
v1
/
models
Create a new analysis model
curl --request POST \
  --url https://api.example.com/v1/models \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "Customer Service Evaluation v2",
  "description": "Comprehensive evaluation model for customer service calls",
  "prompt": "Evaluate the call based on professional standards...",
  "template_variables": [
    {
      "key": "greeting_quality",
      "type": "INTEGER",
      "required": true
    },
    {
      "key": "resolution_achieved",
      "type": "BOOLEAN",
      "required": true
    }
  ],
  "transcription_prompt": "Customer service call for telecom company.",
  "summarize_call": true,
  "summarize_prompt": "Summarize the key points of this call.",
  "neurascore_template": false,
  "enabled": true
}
'
{
  "id": 1,
  "client_id": "client_abc123",
  "name": "Customer Service Evaluation v2",
  "description": "Comprehensive evaluation model for customer service calls",
  "prompt": "<string>",
  "summarize_call": true,
  "neurascore_template": false,
  "enabled": true,
  "created_at": "2023-11-07T05:31:56Z",
  "created_by": "<string>",
  "template_metadata": [],
  "transcription_prompt": "Customer service call for telecom company.",
  "summarize_prompt": "Summarize the key points of this call.",
  "updated_at": "2023-11-07T05:31:56Z",
  "updated_by": "<string>"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request body for creating or updating an analysis model

​
name
string
required

Unique name for this analysis model

Required string length: 1 - 255
Example:

"Customer Service Evaluation v2"

​
description
string
required

Detailed description of what this model evaluates

Example:

"Comprehensive evaluation model for customer service calls including greeting, problem resolution, and closing."

​
prompt
string
required

Analysis configuration defining evaluation criteria and scoring rules

​
template_variables
TemplateVariable · object[]

List of variables to extract during analysis

​
transcription_prompt
string
default:""

Custom prompt to guide audio transcription. Include domain-specific vocabulary, proper nouns, or context to improve accuracy.

Example:

"This is a customer service call for a telecommunications company."

​
summarize_call
boolean
default:false

Enable automatic call summary generation after analysis

Example:

true

​
summarize_prompt
string
default:""

Custom prompt for summary generation. Only used if summarize_call is true.

Example:

"Summarize the key points of this customer service call."

​
neurascore_template
boolean
default:false

Whether this model uses the NeuraScore scoring system

Example:

false

​
enabled
boolean
default:true

Whether this model is active. Disabled models are hidden from listings.

Example:

true

Response

Successful Response

Analysis model details and configuration

​
id
integer
required

Unique identifier for this model

Example:

1

​
client_id
string
required

Owner client identifier

Example:

"client_abc123"

​
name
string
required

Model name

Example:

"Customer Service Evaluation v2"

​
description
string
required

Detailed description of the model

Example:

"Comprehensive evaluation model for customer service calls"

​
prompt
string
required

Analysis configuration and evaluation criteria

​
summarize_call
boolean
required

Whether automatic summary generation is enabled

Example:

true

​
neurascore_template
boolean
required

Whether this model uses the NeuraScore scoring system

Example:

false

​
enabled
boolean
required

Whether this model is active and available for use

Example:

true

​
created_at
string<date-time>
required

Timestamp when model was created (UTC)

​
created_by
string
required

Creator identifier

​
template_metadata
ClientTemplateMetadata · object[]

Configured metadata fields for additional data extraction

​
transcription_prompt
string
default:""

Custom prompt for audio transcription

Example:

"Customer service call for telecom company."

​
summarize_prompt
string
default:""

Custom prompt for summary generation

Example:

"Summarize the key points of this call."

​
updated_at
string<date-time>

Timestamp of last update (UTC)

​
updated_by
string

Last updater identifier