Cekura · Schema

SchemaPostAIAgentV2

CompanyVoice AIQATestingBenchmarking

Properties

Name Type Description
id integer Agent ID. Example: `2142`
name string Agent name. Optional when configure_from_provider is set — it's fetched from the provider.
description string A detailed description of what this agent does and how it should interact Example: ```text AI agent for handling customer support inquiries and resolving technical issues ```
project integer The project this agent belongs to
language string The primary language this agent uses for communication (e.g. 'en' for English) * `af` - Afrikaans * `ar` - Arabic * `bn` - Bengali * `bg` - Bulgarian * `zh` - Chinese Simplified * `cs` - Czech * `da`
telephony object Phone and SIP/websocket channel configuration.
provider object AI platform integration. Nested credentials replace the flat {provider}_api_key fields.
agent_speaks_first booleannull True = agent speaks first; False = test user speaks first; null = auto-detect.
predefined_metrics object predefined metrics to use for the agent
knowledge_base_files array Full desired set of knowledge base files. Reference existing by `id`; add new ones with `file_name` + `content_base64`. Omitted existing files are deleted.
enabled_personalities array Personality profiles enabled for this agent Example: `[1, 2, 3]`
webhook_url string Webhook URL for this agent. When set, overrides the project-level webhook URL for events from this agent.
webhook_secret string Secret sent in X-CEKURA-SECRET header. Applies when agent webhook_url is set. Write-only — never returned in API responses. Use `webhook_secret_configured` to check whether one is set.
webhook_secret_configured string
mock_tools array Full desired set of mock tools. Items with `id` (or a matching `name`) update existing tools; items without create new ones. Omitted existing tools are deleted.
mock_tools_enabled boolean Whether mock tools should be selected by default when configuring a run.
mock_tools_provider stringnull Provider the mock tools were fetched from (vapi, retell, elevenlabs, custom). Null until auto-fetch has been run.
dynamic_variables array Full desired set of dynamic variable definitions, matched by name. Omitted existing variables are deleted.
created_at string Timestamp when the agent was created Example: `"2021-01-01T00:00:00Z"`
updated_at string Timestamp when the agent was last updated Example: `"2021-01-01T00:00:00Z"`
email_id stringnull Email address this agent receives at. When set, enables email-based test runs.
View JSON Schema on GitHub

JSON Schema

cekura-ai-schema-post-aiagent-v2-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-schema-post-aiagent-v2-schema.json",
  "title": "SchemaPostAIAgentV2",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/cekura-ai-ai-agents-api-openapi.yml#/components/schemas/SchemaPostAIAgentV2",
  "type": "object",
  "properties": {
    "id": {
      "type": "integer",
      "readOnly": true,
      "description": "Agent ID.\nExample: `2142`"
    },
    "name": {
      "type": "string",
      "description": "Agent name. Optional when configure_from_provider is set — it's fetched from the provider.",
      "maxLength": 255
    },
    "description": {
      "type": "string",
      "description": "\nA detailed description of what this agent does and how it should interact\nExample: \n```text\nAI agent for handling customer support inquiries and resolving technical issues\n```\n"
    },
    "project": {
      "type": "integer",
      "description": "The project this agent belongs to"
    },
    "language": {
      "enum": [
        "af",
        "ar",
        "bn",
        "bg",
        "zh",
        "cs",
        "da",
        "nl",
        "en",
        "et",
        "fi",
        "fr",
        "de",
        "el",
        "gu",
        "hi",
        "he",
        "hu",
        "id",
        "it",
        "ja",
        "kn",
        "kk",
        "ko",
        "ms",
        "ml",
        "mr",
        "multi",
        "no",
        "pl",
        "pa",
        "pt",
        "ro",
        "ru",
        "sk",
        "es",
        "sv",
        "th",
        "tr",
        "tl",
        "ta",
        "te",
        "uk",
        "uz",
        "vi"
      ],
      "type": "string",
      "x-spec-enum-id": "f996e9ef7edb7fea",
      "default": "en",
      "description": "\nThe primary language this agent uses for communication (e.g. 'en' for English)\n\n\n* `af` - Afrikaans\n* `ar` - Arabic\n* `bn` - Bengali\n* `bg` - Bulgarian\n* `zh` - Chinese Simplified\n* `cs` - Czech\n* `da` - Danish\n* `nl` - Dutch\n* `en` - English\n* `et` - Estonian\n* `fi` - Finnish\n* `fr` - French\n* `de` - German\n* `el` - Greek\n* `gu` - Gujarati\n* `hi` - Hindi\n* `he` - Hebrew\n* `hu` - Hungarian\n* `id` - Indonesian\n* `it` - Italian\n* `ja` - Japanese\n* `kn` - Kannada\n* `kk` - Kazakh\n* `ko` - Korean\n* `ms` - Malay\n* `ml` - Malayalam\n* `mr` - Marathi\n* `multi` - Multilingual\n* `no` - Norwegian\n* `pl` - Polish\n* `pa` - Punjabi\n* `pt` - Portuguese\n* `ro` - Romanian\n* `ru` - Russian\n* `sk` - Slovak\n* `es` - Spanish\n* `sv` - Swedish\n* `th` - Thai\n* `tr` - Turkish\n* `tl` - Tagalog\n* `ta` - Tamil\n* `te` - Telugu\n* `uk` - Ukrainian\n* `uz` - Uzbek\n* `vi` - Vietnamese"
    },
    "telephony": {
      "allOf": [
        {
          "$ref": "#/$defs/AgentTelephony"
        }
      ],
      "writeOnly": true,
      "description": "Phone and SIP/websocket channel configuration."
    },
    "provider": {
      "allOf": [
        {
          "$ref": "#/$defs/SchemaAgentProviderCreate"
        }
      ],
      "writeOnly": true,
      "description": "AI platform integration. Nested credentials replace the flat {provider}_api_key fields."
    },
    "agent_speaks_first": {
      "type": [
        "boolean",
        "null"
      ],
      "description": "True = agent speaks first; False = test user speaks first; null = auto-detect."
    },
    "predefined_metrics": {
      "writeOnly": true,
      "description": "predefined metrics to use for the agent"
    },
    "knowledge_base_files": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/AgentKnowledgeBaseFileWrite"
      },
      "writeOnly": true,
      "description": "Full desired set of knowledge base files. Reference existing by `id`; add new ones with `file_name` + `content_base64`. Omitted existing files are deleted."
    },
    "enabled_personalities": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "readOnly": true,
      "description": "\nPersonality profiles enabled for this agent\nExample: `[1, 2, 3]`\n"
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "description": "Webhook URL for this agent. When set, overrides the project-level webhook URL for events from this agent."
    },
    "webhook_secret": {
      "type": "string",
      "writeOnly": true,
      "description": "Secret sent in X-CEKURA-SECRET header. Applies when agent webhook_url is set. Write-only — never returned in API responses. Use `webhook_secret_configured` to check whether one is set."
    },
    "webhook_secret_configured": {
      "type": "string",
      "readOnly": true
    },
    "mock_tools": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/AgentMockToolWrite"
      },
      "writeOnly": true,
      "description": "Full desired set of mock tools. Items with `id` (or a matching `name`) update existing tools; items without create new ones. Omitted existing tools are deleted."
    },
    "mock_tools_enabled": {
      "type": "boolean",
      "description": "Whether mock tools should be selected by default when configuring a run."
    },
    "mock_tools_provider": {
      "type": [
        "string",
        "null"
      ],
      "readOnly": true,
      "description": "Provider the mock tools were fetched from (vapi, retell, elevenlabs, custom). Null until auto-fetch has been run."
    },
    "dynamic_variables": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/AgentDynamicVariableWrite"
      },
      "writeOnly": true,
      "description": "Full desired set of dynamic variable definitions, matched by name. Omitted existing variables are deleted."
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "readOnly": true,
      "description": "\nTimestamp when the agent was created\nExample: `\"2021-01-01T00:00:00Z\"`\n"
    },
    "updated_at": {
      "type": "string",
      "format": "date-time",
      "readOnly": true,
      "description": "\nTimestamp when the agent was last updated\nExample: `\"2021-01-01T00:00:00Z\"`\n"
    },
    "email_id": {
      "type": [
        "string",
        "null"
      ],
      "format": "email",
      "description": "Email address this agent receives at. When set, enables email-based test runs.",
      "maxLength": 254
    }
  },
  "required": [
    "description"
  ],
  "$defs": {
    "AgentCredentials": {
      "type": "object",
      "description": "Nested credentials block inside the provider object.",
      "properties": {
        "api_key": {
          "type": "string",
          "writeOnly": true,
          "description": "API key or client secret for the provider (write-only — never returned). Required for: vapi, retell, elevenlabs, bland, livekit, pipecat, synthflow, telnyx, assemblyai, smallest. koreai and genesys use their client secret (passed as api_key); cisco only when using a customer-owned Service App. Not needed for: self_hosted, gemini_cx (Cekura impersonates config.service_account_email; no key)."
        },
        "config": {
          "oneOf": [
            {
              "$ref": "#/$defs/ProviderCredentialsConfig"
            },
            {
              "type": "null"
            }
          ]
        }
      }
    },
    "AgentDynamicVariableWrite": {
      "type": "object",
      "description": "One dynamic variable entry in the v2 agent write payload (request side of `dynamic_variables`).",
      "properties": {
        "id": {
          "type": "integer",
          "description": "Ignored on write — variables are matched by name."
        },
        "name": {
          "type": "string",
          "description": "Variable name exactly as it appears in the agent context.",
          "maxLength": 255
        },
        "description": {
          "type": "string",
          "description": "What the variable represents and its expected format."
        }
      },
      "required": [
        "description",
        "name"
      ]
    },
    "AgentKnowledgeBaseFileWrite": {
      "type": "object",
      "description": "One knowledge base file entry in the v2 agent write payload (request side of `knowledge_base_files`).",
      "properties": {
        "id": {
          "type": "integer",
          "description": "ID of an existing file to keep. Files omitted from the list are deleted."
        },
        "file_name": {
          "type": "string",
          "description": "Name for a new file, including extension (pdf, txt, json, csv, xml, md)."
        },
        "name": {
          "type": "string",
          "description": "Alias for file_name."
        },
        "content_base64": {
          "type": "string",
          "description": "Base64-encoded content for a new file. A data-URI prefix is accepted."
        }
      }
    },
    "AgentMockToolServedViaWrite": {
      "type": "object",
      "description": "Runtime routing for a mock tool on write (request side of `mock_tools[].served_via`).",
      "properties": {
        "type": {
          "enum": [
            "direct",
            "mcp"
          ],
          "type": "string",
          "x-spec-enum-id": "b34eaed2d733c895",
          "default": "direct",
          "description": "'direct' = per-tool webhook URL (default). 'mcp' = served through an MCP endpoint; requires mock_index.\n\n* `direct` - direct\n* `mcp` - mcp"
        },
        "mock_index": {
          "type": "integer",
          "minimum": 1,
          "description": "MCP endpoint index (1-based). Tools sharing an index are served by the same MCP endpoint. Required when type='mcp'."
        }
      }
    },
    "AgentMockToolWrite": {
      "type": "object",
      "description": "One mock tool entry in the v2 agent write payload (request side of `mock_tools`).",
      "properties": {
        "id": {
          "type": "integer",
          "description": "ID of an existing mock tool to update. Omit to create a new tool (or update by matching name)."
        },
        "name": {
          "type": "string",
          "description": "Tool name. Required for new tools. Alphanumerics, underscores and hyphens only; under 64 characters.",
          "maxLength": 255
        },
        "description": {
          "type": "string",
          "description": "What the tool does."
        },
        "mock_data": {
          "description": "List of {input, output, response?} mappings returned when the tool is called in mock mode. Optional `response` ({status_code, headers, delay_seconds}) simulates a failing or slow tool; `headers` apply to webhook-style tools only. Optional `match` (\"exact\"), `state` and `then` make a mapping strict or depend on earlier calls in the same call; see the tool's `information` field."
        },
        "freetext_params": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Parameter names skipped during mock matching because they are free-text (e.g. [\"notes\", \"reason\"])."
        },
        "served_via": {
          "allOf": [
            {
              "$ref": "#/$defs/AgentMockToolServedViaWrite"
            }
          ],
          "description": "How the agent reaches this tool at runtime. Omit for a direct per-tool URL; set type='mcp' with a mock_index to group tools under a shared MCP endpoint."
        }
      }
    },
    "AgentTelephony": {
      "type": "object",
      "description": "Phone / SIP / websocket voice channel configuration for the agent.",
      "properties": {
        "phone_number": {
          "type": "string",
          "description": "The agent's own E.164 number, not a customer's: Cekura dials it for inbound tests, and the agent's outbound calls come from it. E.g. +14155551234."
        },
        "inbound": {
          "type": "boolean",
          "default": false,
          "description": "True = agent receives inbound calls; False = outbound only. A property of the agent, not of one run: never flip it to change who dials whom. To dial a different number in a run, pass `outbound_phone_number` to the run."
        },
        "sip_uri": {
          "type": [
            "string",
            "null"
          ],
          "description": "SIP URI, e.g. sip:user@domain.com."
        },
        "sip_originating_region": {
          "enum": [
            "us-east",
            "us-west",
            null
          ],
          "type": [
            "string",
            "null"
          ],
          "x-spec-enum-id": "d4fc86b9d59312c1",
          "description": "Optional Twilio SIP region for direct SIP runs: us-east uses us1 and us-west uses us2. Null keeps Twilio's provider default.\n\n* `us-east` - US East\n* `us-west` - US West"
        },
        "sip_auth": {
          "oneOf": [
            {},
            {
              "type": "null"
            }
          ],
          "description": "SIP credentials: {username, password}."
        },
        "websocket_url": {
          "type": [
            "string",
            "null"
          ],
          "description": "Raw-PCM (16kHz 16-bit mono) websocket endpoint Cekura dials to run the whole call over a websocket you host, e.g. wss://your-host/voice."
        },
        "websocket_auth": {
          "oneOf": [
            {},
            {
              "type": "null"
            }
          ],
          "description": "HTTP Basic Auth credentials for the websocket upgrade: {username, password}."
        },
        "outbound_numbers": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Phone numbers authorized for outbound calls (E.164 format). Example: `[\"+14155551234\", \"+14155550000\"]`"
        }
      }
    },
    "AgentforceChatConfig": {
      "type": "object",
      "description": "Agentforce (Salesforce) chat configuration.",
      "properties": {
        "client_secret": {
          "type": "string",
          "description": "OAuth2 client secret for Salesforce authentication."
        },
        "client_id": {
          "type": "string",
          "description": "OAuth2 client ID for Salesforce authentication."
        },
        "domain": {
          "type": "string",
          "description": "Salesforce domain, e.g. https://example.sandbox.my.salesforce.com."
        },
        "agent_id": {
          "type": "string",
          "description": "Agentforce agent ID (0Xx...)."
        }
      },
      "required": [
        "agent_id",
        "client_id",
        "client_secret",
        "domain"
      ],
      "title": "Agentforce"
    },
    "AmazonConnectChatConfig": {
      "type": "object",
      "description": "Amazon Connect chat-widget configuration.",
      "properties": {
        "widget_id": {
          "type": "string",
          "description": "Chat-widget UUID from the Amazon Connect console."
        },
        "snippet_id": {
          "type": "string",
          "description": "Base64-encoded KMS snippet from your Amazon Connect chat widget."
        },
        "connect_host": {
          "type": "string",
          "description": "Amazon Connect instance host, e.g. acme.my.connect.aws."
        },
        "region": {
          "type": "string",
          "description": "AWS region for the Connect instance. Defaults to us-east-1."
        }
      },
      "required": [
        "connect_host",
        "snippet_id",
        "widget_id"
      ]
    },
    "AmazonConnectConfig": {
      "type": "object",
      "description": "Amazon Connect provider configuration.",
      "properties": {
        "widget_id": {
          "type": "string",
          "description": "Chat widget UUID from the Amazon Connect console."
        },
        "snippet_id": {
          "type": "string",
          "description": "Base64-encoded KMS snippet from your Amazon Connect chat widget."
        },
        "connect_host": {
          "type": "string",
          "description": "Amazon Connect instance host, e.g. acme.my.connect.aws."
        },
        "region": {
          "type": "string",
          "description": "AWS region for the Connect instance. Defaults to us-east-1."
        }
      }
    },
    "AssemblyAIConfig": {
      "type": "object",
      "description": "AssemblyAI Voice Agent API provider configuration. The API key goes in credentials.api_key, the agent id in provider.agent_id.",
      "properties": {
        "region": {
          "enum": [
            "us",
            "eu"
          ],
          "type": "string",
          "x-spec-enum-id": "450cf1402ab1a3c6",
          "description": "AssemblyAI deployment the agent lives in. Defaults to us (phone agents are US-hosted).\n\n* `us` - us\n* `eu` - eu"
        }
      }
    },
    "BlandChatConfig": {
      "type": "object",
      "description": "Bland chat configuration.",
      "properties": {
        "agent_id": {
          "type": "string",
          "description": "The Bland pathway_id to use for text-mode test runs."
        }
      },
      "required": [
        "agent_id"
      ],
      "title": "Bland"
    },
    "BlandConfig": {
      "type": "object",
      "description": "Bland AI provider configuration.",
      "properties": {
        "encrypted_key": {
          "type": "string",
          "description": "Twilio credential bundle for Bland outbound calls. Required when using Bland with Twilio telephony."
        }
      },
      "title": "Bland"
    },
    "ChatAgentConfig": {
      "oneOf": [
        {
          "$ref": "#/$defs/RetellChatConfig"
        },
        {
          "$ref": "#/$defs/BlandChatConfig"
        },
        {
          "$ref": "#/$defs/AgentforceChatConfig"
        },
        {
          "$ref": "#/$defs/SelfHostedChatConfig"
        },
        {
          "$ref": "#/$defs/AmazonConnectChatConfig"
        },
        {
          "$ref": "#/$defs/KoreAiChatConfig"
        },
        {
          "$ref": "#/$defs/SierraChatConfig"
        }
      ]
    },
    "ChatAgentDetails": {
      "type": "object",
      "description": "Chat-mode provider configuration nested inside the provider block.",
      "properties": {
        "type": {
          "enum": [
            "retell",
            "bland",
            "vapi",
            "elevenlabs",
            "livekit",
            "agora",
            "pipecat",
            "sms",
            "whatsapp",
            "self_hosted",
            "agentforce",
            "amazon_connect",
            "koreai",
            "sierra",
            ""
          ],
          "type": "string",
          "x-spec-enum-id": "b896c086cc3529ef",
          "description": "Chat provider type. Must be compatible with the voice provider.type. Valid values: retell, bland, vapi, elevenlabs, livekit, agora, sms, whatsapp, self_hosted, agentforce, amazon_connect, koreai, sierra. Pass an empty string \"\" (or send chat_agent_details: null) to clear the chat overlay.\n\n* `retell` - retell\n* `bland` - bland\n* `vapi` - vapi\n* `elevenlabs` - elevenlabs\n* `livekit` - livekit\n* `agora` - agora\n* `pipecat` - pipecat\n* `sms` - sms\n* `whatsapp` - whatsapp\n* `self_hosted` - self_hosted\n* `agentforce` - agentforce\n* `amazon_connect` - amazon_connect\n* `koreai` - koreai\n* `sierra` - sierra"
        },
        "config": {
          "oneOf": [
            {
              "$ref": "#/$defs/ChatAgentConfig"
            },
            {
              "type": "null"
            }
          ]
        }
      }
    },
    "CiscoConfig": {
      "type": "object",
      "description": "Cisco Webex Contact Center provider configuration.",
      "properties": {
        "org_id": {
          "type": "string",
          "description": "Control Hub organization UUID of the contact center tenant."
        },
        "region": {
          "type": "string",
          "description": "Contact Center datacenter, e.g. us1, eu1, anz1. Defaults to us1."
        },
        "client_id": {
          "type": "string",
          "description": "Service App client ID (pair with the client secret and refresh_token)."
        },
        "refresh_token": {
          "type": "string",
          "writeOnly": true,
          "description": "Service App refresh token; stored encrypted."
        }
      },
      "required": [
        "org_id"
      ],
      "title": "Cisco Webex"
    },
    "ElevenLabsConfig": {
      "type": "object",
      "description": "ElevenLabs provider configuration.",
      "properties": {
        "trigger_url": {
          "type": "string",
          "description": "URL Cekura calls to create outbound ElevenLabs phone calls."
        },
        "trigger_secret": {
          "type": "string",
          "writeOnly": true,
          "description": "Optional shared secret sent as the X-CEKURA-SECRET header on trigger URL requests, so your endpoint can reject calls it didn't expect. Write-only — responses expose trigger_secret_configured instead."
        },
        "elevenlabs_region": {
          "enum": [
            "us",
            "eu"
          ],
          "type": "string",
          "x-spec-enum-id": "450cf1402ab1a3c6",
          "description": "ElevenLabs API region. 'us' uses api.elevenlabs.io, 'eu' uses api.eu.residency.elevenlabs.io. Defaults to 'us'.\n\n* `us` - us\n* `eu` - eu"
        },
        "elevenlabs_base_url_override": {
          "type": "string",
          "description": "Optional custom base URL for ElevenLabs API. Takes precedence over elevenlabs_region if set."
        },
        "elevenlabs_environment": {
          "type": "string",
          "description": "ElevenLabs environment used to resolve the agent's environment variables (tool URLs, secrets, headers) on test runs, e.g. test. Must match an environment configured in ElevenLabs. Omit or send blank to use production."
        },
        "elevenlabs_branch_id": {
          "type": "string",
          "description": "ElevenLabs agent branch to run conversations against. Omit or send blank to use the agent's default branch."
        }
      },
      "title": "ElevenLabs"
    },
    "GeminiEnterpriseCxConfig": {
      "type": "object",
      "description": "Gemini Enterprise CX (Google CX Agent Studio) provider configuration. No API key: Cekura impersonates the reader service account.",
      "properties": {
        "service_account_email": {
          "type": "string",
          "description": "Your reader service account (name@project.iam.gserviceaccount.com) that Cekura's per-agent identity is allowed to act as."
        },
        "project_id": {
          "type": "string",
          "description": "GCP project that hosts the agent. Defaults to the project named in the service-account email."
        },
        "location": {
          "type": "string",
          "description": "Agent region, e.g. us-central1 or global. The CX agent id goes in provider.agent_id."
        }
      },
      "required": [
        "location",
        "service_account_email"
      ],
      "title": "Gemini Enterprise CX"
    },
    "GenesysConfig": {
      "type": "object",
      "description": "Genesys Cloud provider configuration.",
      "properties": {
        "client_id": {
          "type": "string",
          "description": "Genesys Cloud OAuth2 Client ID."
        },
        "region": {
          "type": "string",
          "description": "Genesys Cloud region, e.g. us-east-1."
        }
      },
      "required": [
        "client_id",
        "region"
      ],
      "title": "Genesys"
    },
    "KoreAiChatConfig": {
      "type": "object",
      "description": "Kore.ai XO chat configuration.",
      "properties": {
        "api_secret": {
          "type": "string",
          "writeOnly": true,
          "description": "Kore XO Web/Mobile Client API key. Encrypted at rest."
        },
        "api_secret_configured": {
          "type": "boolean",
          "readOnly": true,
          "description": "Whether the Kore XO Web/Mobile Client API key is configured."
        },
        "host": {
          "type": "string",
          "description": "Kore XO host. Defaults to platform.kore.ai."
        },
        "rtm_signing_public_key": {
          "type": "string",
          "description": "Optional Kore secure-RTM ECDSA P-256 public-key PEM used to verify the provider handshake."
        },
        "allow_unverified_secure_rtm": {
          "type": "boolean",
          "description": "Allow secure RTM without a signing-key pin. Defaults to true for existing credentials; set false to require rtm_signing_public_key."
        }
      }
    },
    "KoreAiConfig": {
      "type": "object",
      "description": "Kore.ai provider configuration. XO platform (default) uses api_key + client_id + bot_id; the Artemis agent platform uses the artemis_* keys. Both sets can be stored side by side; platform selects the active one.",
      "properties": {
        "platform": {
          "enum": [
            "xo",
            "artemis"
          ],
          "type": "string",
          "x-spec-enum-id": "b86d1a405f4d0697",
          "description": "Kore product the agent runs on: \"xo\" (default) or \"artemis\".\n\n* `xo` - xo\n* `artemis` - artemis"
        },
        "client_id": {
          "type": "string",
          "description": "KoreAI OAuth2 Client ID. XO platform."
        },
        "bot_id": {
          "type": "string",
          "description": "KoreAI Bot ID to connect to. XO platform."
        },
        "host": {
          "type": "string",
          "description": "KoreAI XO host. Defaults to bots.kore.ai."
        },
        "artemis_api_key": {
          "type": "string",
          "writeOnly": true,
          "description": "Artemis project-bound x-api-key. Encrypted at rest; returned as artemis_api_key_configured."
        },
        "artemis_host": {
          "type": "string",
          "description": "Artemis host, e.g. ind-agents.kore.ai."
        },
        "artemis_project_id": {
          "type": "string",
          "description": "Artemis project ID the API key is bound to."
        }
      },
      "title": "Kore.ai"
    },
    "LiveKitConfig": {
      "type": "object",
      "description": "LiveKit provider configuration.",
      "properties": {
        "api_secret": {
          "type": "string",
          "description": "LiveKit API secret. Required alongside api_key."
        },
        "url": {
          "type": "string",
          "description": "LiveKit server WebSocket URL, e.g. wss://acme.livekit.cloud."
        },
        "agent_name": {
          "type": "string",
          "description": "LiveKit agent name to connect to."
        },
        "config": {
          "description": "Additional LiveKit configuration as a JSON object."
        },
        "tracing_enabled": {
          "type": "boolean",
          "description": "Enable LiveKit tracing (requires Cekura SDK integrated in your LiveKit agent)."
        },
        "trigger_url": {
          "type": "string",
          "description": "URL Cekura calls to create outbound phone calls."
        },
        "trigger_secret": {
          "type": "string",
          "writeOnly": true,
          "description": "Optional shared secret sent as the X-CEKURA-SECRET header on trigger URL requests, so your endpoint can reject calls it didn't expect. Write-only — responses expose trigger_secret_configured instead."
        }
      },
      "required": [
        "api_secret",
        "url"
      ],
      "title": "LiveKit"
    },
    "PipecatConfig": {
      "type": "object",
      "description": "Pipecat provider configuration.",
      "properties": {
        "pipecat_agent_name": {
          "type": "string",
          "description": "Name of the Pipecat agent. Required when tracing_enabled is false."
        },
        "config": {
          "description": "Additional agent configuration as a JSON object."
        },
        "room_properties": {
          "description": "Room properties configuration as a JSON object."
        },
        "webhook_url": {
          "type": "string",
          "description": "Webhook URL for Pipecat call events."
        },
        "tracing_enabled": {
          "type": "boolean",
          "description": "Enable Pipecat tracing (requires Cekura SDK integrated in your Pipecat agent). When true, pipecat_agent_name is not required."
        }
      },
      "title": "Pipecat"
    },
    "ProviderCredentialsConfig": {
      "oneOf": [
        {
          "$ref": "#/$defs/VapiConfig"
        },
        {
          "$ref": "#/$defs/RetellConfig"
        },
        {
          "$ref": "#/$defs/ElevenLabsConfig"
        },
        {
          "$ref": "#/$defs/BlandConfig"
        },
        {
          "$ref": "#/$defs/LiveKitConfig"
        },
        {
          "$ref": "#/$defs/SynthflowConfig"
        },
        {
          "$ref": "#/$defs/KoreAiConfig"
        },
        {
          "$ref": "#/$defs/GenesysConfig"
        },
        {
          "$ref": "#/$defs/CiscoConfig"
        },
        {
          "$ref": "#/$defs/GeminiEnterpriseCxConfig"
        },
        {
          "$ref": "#/$defs/AssemblyAIConfig"
        },
        {
          "$ref": "#/$defs/PipecatConfig"
        },
        {
          "$ref": "#/$defs/SelfHostedConfig"
        },
        {
          "$ref": "#/$defs/AmazonConnectConfig"
        }
      ]
    },
    "RetellChatConfig": {
      "type": "object",
      "description": "Retell chat configuration.",
      "properties": {
        "agent_id": {
          "type": "string",
          "description": "The Retell chat agent ID to use for text-mode test runs. Optional — when omitted, a temporary chat agent is cloned from the voice agent for each run."
        }
      },
      "title": "Retell"
    },
    "RetellConfig": {
      "type": "object",
      "description": "Retell provider configuration.",
      "properties": {
        "trigger_url": {
          "type": "string",
          "description": "URL Cekura calls to create outbound Retell phone calls."
        },
        "trigger_secret": {
          "type": "string",
          "writeOnly": true,
          "description": "Optional shared secret sent as the X-CEKURA-SECRET header on trigger URL requests, so your endpoint can reject calls it didn't expect. Write-only — responses expose trigger_secret_configured instead."
        }
      },
      "title": "Retell"
    },
    "SchemaAgentProviderCreate": {
      "type": "object",
      "properties": {
        "type": {
          "enum": [
            "vapi",
            "retell",
            "elevenlabs",
            "agentforce",
            "cisco",
            "bland",
            "livekit",
            "pipecat",
            "synthflow",
            "agora",
            "koreai",
            "genesys",
            "amazon_connect",
            "telnyx",
            "gemini_cx",
            "assemblyai",
            "smallest",
            "custom",
            ""
          ],
          "type": "string",
          "x-spec-enum-id": "344119656d78c0bb",
          "description": "Voice/inbound platform provider type. Valid values: vapi, retell, elevenlabs, bland, livekit, cisco, gemini_cx, assemblyai, smallest, synthflow, koreai, genesys, amazon_connect, pipecat, custom. Use 'custom' (or omit) for chat-only agents with no voice provider — the chat channel goes in chat_agent_details.type. For a raw-PCM websocket voice agent you host yourself, use type='custom' and put the endpoint in telephony.websocket_url. Text-only channels (sms, whatsapp, agentforce, sierra) belong in chat_agent_details.type, not here.\n\n* `vapi` - Vapi\n* `retell` - Retell\n* `elevenlabs` - Elevenlabs\n* `agentforce` - Agentforce\n* `cisco` - Cisco\n* `bland` - Bland\n* `livekit` - Livekit\n* `pipecat` - Pipecat\n* `synthflow` - Synthflow\n* `agora` - Agora\n* `koreai` - Koreai\n* `genesys` - Genesys\n* `amazon_connect` - Amazon Connect\n* `telnyx` - Telnyx\n* `gemini_cx` - Gemini Enterprise CX\n* `assemblyai` - AssemblyAI\n* `smallest` - Smallest AI\n* `custom` - Custom (chat-only, no voice provider)"
        },
        "agent_id": {
          "type": [
            "string",
            "null"
          ],
          "description": "Agent ID for voice/inbound runs on the provider's platform. For vapi, elevenlabs, retell, synthflow, telnyx, assemblyai, smallest, and bland this is the voice agent ID (for bland it's the persona_id). Bland's pathway_id and retell's chat agent ID go in chat_agent_details.config.agent_id."
        },
        "credentials": {
          "oneOf": [
            {
              "$ref": "#/$defs/AgentCredentials"
            },
            {
              "type": "n

# --- truncated at 32 KB (40 KB total) ---
# Full source: https://artifacts.apis.io/cekura-ai/json-schema/cekura-ai-schema-post-aiagent-v2-schema.json

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/cekura-ai-schema-post-aiagent-v2"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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.