Skip to main content
POST
/
v1
/
api
/
agents
Create Call Agent
curl --request POST \
  --url https://api.trillet.ai/v1/api/agents \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <x-api-key>' \
  --header 'x-workspace-id: <x-workspace-id>' \
  --data '{
  "name": "<string>",
  "ttsModel": {
    "provider": "<string>",
    "voiceId": "<string>",
    "language": "<string>",
    "elevenLabsApiKey": "<string>"
  },
  "smartCallback": true,
  "maxAttemptsForSmartCallback": 123,
  "gapBetweenEachAttemptForSmartCallback": [
    {
      "days": 123,
      "hours": 123
    }
  ],
  "phoneNumberIds": [
    {}
  ],
  "llmModel": "<string>",
  "settings": {
    "speed": 123,
    "volume": 123,
    "temperature": 123
  },
  "variables": {}
}'
{
  "name": "Customer Support Agent",
  "ttsModel": {
    "provider": "rime",
    "voiceId": "mistv2_Wildflower",
    "name": "Sophie",
    "language": "en"
  },
  "llmModel": "gpt-4o",
  "type": "voice",
  "smartCallback": true,
  "maxAttemptsForSmartCallback": 3,
  "gapBetweenEachAttemptForSmartCallback": [
    { "days": 1, "hours": 2 },
    { "days": 2, "hours": 0 },
    { "days": 3, "hours": 6 }
  ],
  "settings": {
    "speed": 0.8,
    "volume": 1,
    "temperature": 0.7
  }
}

​
Headers

​
x-api-key
string
required
API key used for authenticating requests to the API.
​
x-workspace-id
string
required
Workspace identifier for the API.

​
Request Body

​
name
string
required
Name of the agent being created.
​
ttsModel
object
required
Text-to-Speech (TTS) configuration for the agent.
​
smartCallback
boolean
default:"false"
Enable smart callback functionality for the agent.
​
maxAttemptsForSmartCallback
number
default:"5"
Maximum number of callback attempts when smart callback is enabled.
​
gapBetweenEachAttemptForSmartCallback
array
Array of time intervals between each callback attempt. Each item contains days and hours.
​
phoneNumberIds
array
Array of phone number IDs to associate with the agent.
​
llmModel
string
default:"gpt-4o-mini"
required
Language Model to be used by the agent to generate responses. Must be one of: gpt-4o-mini, gpt-4o-enterprise, gpt-4.1, gpt-4.1-mini, gemini-2.5-flash-preview-native-audio-dialog, gemini-2.5-flash, gemini-live-2.5-flash-preview, geminiaudiopipeline:gemini-2.5-flash-preview-native-audio-dialog, gemini-2.0-flash-live-001, gpt-5.
​
settings
object
Additional settings for the agent.
​
variables
object
Custom variables to store for the agent.

​
Response Fields

​
_id
string
Unique identifier for the newly created agent.
​
workspaceId
string
Workspace ID associated with the agent.
​
userId
string
User ID of the agent creator.
​
name
string
Name of the agent.
​
ttsModel
object
Text-to-Speech configuration for the agent.
​
provider
string
TTS provider used by the agent.
​
voiceId
string
default:"mistv2_Wildflower"
Voice ID used for generating speech. (e.g., mistv2_Brook, mistv2_Violet, mistv2_Wildflower)
​
language
string
Language code of the TTS voice.
​
elevenLabsApiKey
string
Encrypted ElevenLabs API key (only present if provider is “11labs_byo”).
​
llmModel
string
Language Model used by the agent to generate responses.
​
smartCallback
boolean
Whether smart callback is enabled for the agent.
​
maxAttemptsForSmartCallback
number
Maximum number of callback attempts.
​
gapBetweenEachAttemptForSmartCallback
array
Array of time intervals between callback attempts.
​
phoneNumberIds
array
Array of phone number IDs associated with the agent.
​
activeSessions
array
Array of active sessions for the agent.
​
settings
object
Additional settings configured for the agent.
​
status
string
Current status of the agent (pending, ready, or error).
​
currentNode
string
Current node or state within the agent’s flow.
​
variables
object
Custom variables stored for the agent.
​
createdAt
string
Timestamp when the agent was created.
​
updatedAt
string
Timestamp when the agent was last updated.
{
  "name": "Customer Support Agent",
  "ttsModel": {
    "provider": "rime",
    "voiceId": "mistv2_Wildflower",
    "name": "Sophie",
    "language": "en"
  },
  "llmModel": "gpt-4o",
  "type": "voice",
  "smartCallback": true,
  "maxAttemptsForSmartCallback": 3,
  "gapBetweenEachAttemptForSmartCallback": [
    { "days": 1, "hours": 2 },
    { "days": 2, "hours": 0 },
    { "days": 3, "hours": 6 }
  ],
  "settings": {
    "speed": 0.8,
    "volume": 1,
    "temperature": 0.7
  }
}