Create Call Agent

Create a new agent for a workspace.

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.

Show properties

provider · string · required

TTS provider. Must be one of the following: openai, rime, elevenlabs, 11labs_byo, google.

voiceId · string · required

The voice ID used for generating speech. e.g for Trillet Voices, “mistv2_Wildflower” - Alt Female, Smart “mistv2_Brook” - Male, Friendly “mistv2_Violet” - Female, Professional

language · string · default: "en" · required

Language code (e.g., en, fr).

elevenLabsApiKey · string

ElevenLabs API key (required only when provider is “11labs_byo”). This will be encrypted and stored securely.

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.

Show Array Item Properties

days · number · default: "1"

Number of days to wait before the next attempt.

hours · number · default: "0"

Number of hours to wait before the next attempt.

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.

Show properties

speed · number · default: "0.7"

Value between 0 and 1 that determines how fast the TTS narrates text.

volume · number · default: "1"

Value between 0 and 1 that adjusts the TTS volume.

temperature · number · default: "0.7"

Value between 0 and 1 for controlling the creativity of the LLM.

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.

Response

{
  "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
  }
}