curl -X POST 'https://api.elevenlabs.io/v1/convai/agent-testing/create' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "from_conversation_metadata": {
    "conversation_id": "example-conversation-id",
    "agent_id": "example-agent-id",
    "branch_id": "example-branch-id",
    "workflow_node_id": "example-workflow-node-id",
    "original_agent_reply": []
  },
  "dynamic_variables": {},
  "chat_history": [
    {
      "role": "user",
      "agent_metadata": {
        "agent_id": "example-agent-id",
        "branch_id": "example-branch-id",
        "workflow_node_id": "example-workflow-node-id",
        "version_id": "example-version-id"
      },
      "message": "example-message",
      "multivoice_message": {
        "parts": [
          {
            "text": "[recursive or deeply nested schema]",
            "voice_label": "[recursive or deeply nested schema]",
            "time_in_call_secs": "[recursive or deeply nested schema]"
          }
        ]
      },
      "tool_calls": [
        {
          "type": "system",
          "request_id": "example-request-id",
          "tool_name": "example-tool-name",
          "tool_id": "example-tool-id",
          "params_as_json": "example-params-as-json",
          "tool_has_been_called": true,
          "tool_details": {
            "type": "[recursive or deeply nested schema]",
            "method": "[recursive or deeply nested schema]",
            "url": "[recursive or deeply nested schema]",
            "headers": "[recursive or deeply nested schema]",
            "path_params": "[recursive or deeply nested schema]",
            "query_params": "[recursive or deeply nested schema]",
            "body": "[recursive or deeply nested schema]"
          }
        }
      ],
      "tool_results": [
        {
          "request_id": "example-request-id",
          "tool_name": "example-tool-name",
          "result_value": "example-result-value",
          "is_error": true,
          "is_blocked": false,
          "tool_has_been_called": true,
          "tool_latency_secs": 0,
          "error_type": "",
          "raw_error_message": "",
          "dynamic_variable_updates": [
            "[recursive or deeply nested schema]"
          ],
          "type": "client"
        }
      ],
      "feedback": {
        "score": "like",
        "time_in_call_secs": 0
      },
      "llm_override": "example-llm-override",
      "producing_llm": "example-producing-llm",
      "time_in_call_secs": 0,
      "conversation_turn_metrics": {
        "metrics": {},
        "convai_asr_provider": "example-convai-asr-provider",
        "convai_tts_model": "example-convai-tts-model",
        "convai_tts_cascade": "example-convai-tts-cascade",
        "voice_id": "example-voice-id"
      },
      "rag_retrieval_info": {
        "chunks": [
          {
            "document_id": "[recursive or deeply nested schema]",
            "chunk_id": "[recursive or deeply nested schema]",
            "vector_distance": "[recursive or deeply nested schema]"
          }
        ],
        "embedding_model": "e5_mistral_7b_instruct",
        "retrieval_query": "example-retrieval-query",
        "rag_latency_secs": 0,
        "used_chunk_ids": [
          "example-used-chunk-ids"
        ]
      },
      "llm_usage": {
        "model_usage": {}
      },
      "interrupted": false,
      "ignored_as_backchannel": false,
      "platform_event": "user_turn_timeout",
      "original_message": "example-original-message",
      "reasoning": [
        {
          "summary": "example-summary",
          "provider_redact": false
        }
      ],
      "source_medium": "audio",
      "source_event_id": 0,
      "used_static_kb_document_ids": [
        "example-used-static-kb-document-ids"
      ],
      "user_identifier": "example-user-identifier",
      "id": "example-id",
      "triggered_guardrails": [
        {
          "guardrail_type": "custom",
          "guardrail_name": "example-guardrail-name"
        }
      ]
    }
  ],
  "conversation_initiation_source": "unknown",
  "environment": "example-environment",
  "type": "llm",
  "success_condition": "",
  "success_examples": [
    {
      "response": "example-response",
      "type": "example-type"
    }
  ],
  "failure_examples": [
    {
      "response": "example-response",
      "type": "example-type"
    }
  ],
  "name": "example-name",
  "parent_folder_id": "parent-folder-id"
}'

# POST /v1/convai/agent-testing/create (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-10-20

> Create Agent Response Test

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/convai/agent-testing/create' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"name":"example-name","from_conversation_metadata":{"conversation_id":"example-conversation-id","agent_id":"example-agent-id"}}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| name | body | string | Yes | Request body field name. |
| from_conversation_metadata | body | object | No | Metadata of a conversation this test... |
| dynamic_variables | body | object | No | Dynamic variables to replace in the a... |
Other params: chat_history, conversation_initiation_source, environment, type, success_condition, success_examples, failure_examples, parent_folder_id

## Response (200 OK)
{"id":"string"}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

POST /v1/convai/agent-testing/create — ElevenLabs API

ElevenLabs API

Create Agent Response Test

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-10-20 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 224 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/convai/agent-testing/create' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "from_conversation_metadata": {    "conversation_id": "example-conversation-id",    "agent_id": "example-agent-id",    "branch_id": "example-branch-id",    "workflow_node_id": "example-workflow-node-id",    "original_agent_reply": []  },  "dynamic_variables": {},  "chat_history": [    {      "role": "user",      "agent_metadata": {        "agent_id": "example-agent-id",        "branch_id": "example-branch-id",        "workflow_node_id": "example-workflow-node-id",        "version_id": "example-version-id"      },      "message": "example-message",      "multivoice_message": {        "parts": [          {            "text": "[recursive or deeply nested schema]",            "voice_label": "[recursive or deeply nested schema]",            "time_in_call_secs": "[recursive or deeply nested schema]"          }        ]      },      "tool_calls": [        {          "type": "system",          "request_id": "example-request-id",          "tool_name": "example-tool-name",          "tool_id": "example-tool-id",          "params_as_json": "example-params-as-json",          "tool_has_been_called": true,          "tool_details": {            "type": "[recursive or deeply nested schema]",            "method": "[recursive or deeply nested schema]",            "url": "[recursive or deeply nested schema]",            "headers": "[recursive or deeply nested schema]",            "path_params": "[recursive or deeply nested schema]",            "query_params": "[recursive or deeply nested schema]",            "body": "[recursive or deeply nested schema]"          }        }      ],      "tool_results": [        {          "request_id": "example-request-id",          "tool_name": "example-tool-name",          "result_value": "example-result-value",          "is_error": true,          "is_blocked": false,          "tool_has_been_called": true,          "tool_latency_secs": 0,          "error_type": "",          "raw_error_message": "",          "dynamic_variable_updates": [            "[recursive or deeply nested schema]"          ],          "type": "client"        }      ],      "feedback": {        "score": "like",        "time_in_call_secs": 0      },      "llm_override": "example-llm-override",      "producing_llm": "example-producing-llm",      "time_in_call_secs": 0,      "conversation_turn_metrics": {        "metrics": {},        "convai_asr_provider": "example-convai-asr-provider",        "convai_tts_model": "example-convai-tts-model",        "convai_tts_cascade": "example-convai-tts-cascade",        "voice_id": "example-voice-id"      },      "rag_retrieval_info": {        "chunks": [          {            "document_id": "[recursive or deeply nested schema]",            "chunk_id": "[recursive or deeply nested schema]",            "vector_distance": "[recursive or deeply nested schema]"          }        ],        "embedding_model": "e5_mistral_7b_instruct",        "retrieval_query": "example-retrieval-query",        "rag_latency_secs": 0,        "used_chunk_ids": [          "example-used-chunk-ids"        ]      },      "llm_usage": {        "model_usage": {}      },      "interrupted": false,      "ignored_as_backchannel": false,      "platform_event": "user_turn_timeout",      "original_message": "example-original-message",      "reasoning": [        {          "summary": "example-summary",          "provider_redact": false        }      ],      "source_medium": "audio",      "source_event_id": 0,      "used_static_kb_document_ids": [        "example-used-static-kb-document-ids"      ],      "user_identifier": "example-user-identifier",      "id": "example-id",      "triggered_guardrails": [        {          "guardrail_type": "custom",          "guardrail_name": "example-guardrail-name"        }      ]    }  ],  "conversation_initiation_source": "unknown",  "environment": "example-environment",  "type": "llm",  "success_condition": "",  "success_examples": [    {      "response": "example-response",      "type": "example-type"    }  ],  "failure_examples": [    {      "response": "example-response",      "type": "example-type"    }  ],  "name": "example-name",  "parent_folder_id": "parent-folder-id"}'

Parameters

Name	In	Type	Required	Description
from_conversation_metadata	body	object	No	Metadata of a conversation this test was created from (if applicable).
dynamic_variables	body	object	No	Dynamic variables to replace in the agent config during testing
chat_history	body	object[]	No	Request body field chat_history.
conversation_initiation_source	body	string	No	Simulate the test as if the conversation originated from this channel.
environment	body	string	No	The environment to resolve environment-specific variable values against when running this test (URL, headers, auth connections). If not provided, defaults to 'production'. For simulation tests, simulation_environment takes precedence when set.
type	body	string	No	Request body field type.
success_condition	body	string	No	A prompt that evaluates whether the agent's response is successful. Should return True or False.
success_examples	body	object[]	No	Non-empty list of example responses that should be considered successful
failure_examples	body	object[]	No	Non-empty list of example responses that should be considered failures
name	body	string	Yes	Request body field name.
parent_folder_id	body	string	No	The ID of the parent folder. If not provided, the test will be created at the root level.

Response 200 OK

{
  "id": "string"
}

Get a free ElevenLabs API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.