Okareo · Schema

DriverModelSchema

CompanyArtificial IntelligenceSynthetic DataVoice AgentsTesting

Properties

Name Type Description
id object ID of the driver model
name string Name of the driver model
temperature number Temperature of the driver model
model_id object Model ID of the driver model
prompt_template string Prompt template for the driver model
voice_instructions object Voice instructions for the driver model
voice_profile object Voice profile for the driver model. Select from the following list of options: neutral, happy, excited, content, curious, calm, confident, surprised, confused, sad, disappointed, bored, frustrated, an
voice object Voice setting for the driver model. Use GET /v0/voices to retrieve available voice options.
voice_tone object Driver's emotion/tone passed to Cartesia (a canonical tone token, e.g. 'happy', 'frustrated'). Definitive source of the driver's emotion. If omitted but voice_profile is set, it is derived from the pr
language object Language code in BCP-47 format (e.g., 'en-US', 'es-MX', 'ja', 'fr-CA'). For voice targets, improves STT accuracy by constraining language model. If not specified, defaults to 'multi' for automatic lan
project_id object ID for project
tags object Tags are strings that can be used to filter drivers in the Okareo app. Omit to leave existing tags unchanged; send an empty list to clear them.
steps object Scripted Driver: an ordered list of steps ({message}, {dtmf}, {end_conversation}), or one {scenario_input.} reference that resolves to that list per scenario row. end_conversation must be last
View JSON Schema on GitHub

JSON Schema

okareo-driver-model-schema-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/okareo/main/json-schema/okareo-driver-model-schema-schema.json",
  "title": "DriverModelSchema",
  "x-generated": "2026-10-18",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/okareo-openapi.json#/components/schemas/DriverModelSchema",
  "properties": {
    "id": {
      "anyOf": [
        {
          "type": "string",
          "format": "uuid"
        },
        {
          "type": "null"
        }
      ],
      "title": "Id",
      "description": "ID of the driver model"
    },
    "name": {
      "type": "string",
      "title": "Name",
      "description": "Name of the driver model"
    },
    "temperature": {
      "type": "number",
      "title": "Temperature",
      "description": "Temperature of the driver model"
    },
    "model_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Model Id",
      "description": "Model ID of the driver model"
    },
    "prompt_template": {
      "type": "string",
      "title": "Prompt Template",
      "description": "Prompt template for the driver model"
    },
    "voice_instructions": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Voice Instructions",
      "description": "Voice instructions for the driver model"
    },
    "voice_profile": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Voice Profile",
      "description": "Voice profile for the driver model. Select from the following list of options: neutral, happy, excited, content, curious, calm, confident, surprised, confused, sad, disappointed, bored, frustrated, angry, agitated, anxious, scared, sarcastic."
    },
    "voice": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Voice",
      "description": "Voice setting for the driver model. Use GET /v0/voices to retrieve available voice options."
    },
    "voice_tone": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Voice Tone",
      "description": "Driver's emotion/tone passed to Cartesia (a canonical tone token, e.g. 'happy', 'frustrated'). Definitive source of the driver's emotion. If omitted but voice_profile is set, it is derived from the profile."
    },
    "language": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Language",
      "description": "Language code in BCP-47 format (e.g., 'en-US', 'es-MX', 'ja', 'fr-CA'). For voice targets, improves STT accuracy by constraining language model. If not specified, defaults to 'multi' for automatic language detection."
    },
    "project_id": {
      "anyOf": [
        {
          "type": "string",
          "format": "uuid"
        },
        {
          "type": "null"
        }
      ],
      "title": "Project Id",
      "description": "ID for project"
    },
    "tags": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "title": "Tags",
      "description": "Tags are strings that can be used to filter drivers in the Okareo app. Omit to leave existing tags unchanged; send an empty list to clear them."
    },
    "steps": {
      "anyOf": [
        {
          "items": {
            "$ref": "#/$defs/DriverStepSchema"
          },
          "type": "array"
        },
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Steps",
      "description": "Scripted Driver: an ordered list of steps ({message}, {dtmf}, {end_conversation}), or one {scenario_input.<column>} reference that resolves to that list per scenario row. end_conversation must be last. When set, prompt_template is not used and no Driver LLM runs."
    }
  },
  "type": "object",
  "required": [
    "name",
    "temperature",
    "prompt_template"
  ],
  "$defs": {
    "DriverStepSchema": {
      "properties": {
        "message": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Message",
          "description": "Words the Driver says, verbatim."
        },
        "dtmf": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Dtmf",
          "description": "Keys the Driver presses (0-9, A-D, *, #, w); voice only."
        },
        "silence": {
          "anyOf": [
            {
              "type": "boolean"
            },
            {
              "type": "null"
            }
          ],
          "title": "Silence",
          "description": "true: the Driver says nothing this turn and listens for the Target's next segment; voice only."
        },
        "end_conversation": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "End Conversation",
          "description": "Closing words; the Driver says them and ends the call."
        },
        "reason": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Reason",
          "description": "Why the script ended the call (with end_conversation only)."
        },
        "turn": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "title": "Turn",
          "description": "Reserved; rejected today."
        }
      },
      "additionalProperties": false,
      "type": "object",
      "title": "DriverStepSchema",
      "description": "One scripted step: exactly one of message / dtmf / end_conversation (checked by the\nsteps validator), with an optional reason on end_conversation. Unknown keys are a 422."
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/okareo-driver-model-schema"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.