Get Test Run | Speechify API

from speechify import Speechify
client = Speechify(
    token="YOUR_TOKEN_HERE",
)
client.tts.agents.get_test_run(
    id="id",
)

{
  "id": "a3f1c9d2-7b4e-4f8a-9c3d-2e5f7a1b8c9d",
  "test_id": "test-987654321",
  "agent_id": "agent-123456789",
  "status": "passed",
  "created_at": "2024-01-15T09:29:59Z",
  "started_at": "2024-01-15T09:30:00Z",
  "completed_at": "2024-01-15T09:30:01Z",
  "result": {
    "test_type": "scenario",
    "passed": true,
    "rationale": "The agent greeted Alice by name as required.",
    "duration_ms": 1240,
    "scenario": {
      "agent_response": "Hi Alice! How can I help you today?",
      "passed": true,
      "rationale": "Response contains the caller's name.",
      "score": 0.95,
      "duration_ms": 1240
    }
  },
  "error": ""
}

Retrieve a single test run by ID. Poll this endpoint until status reaches a terminal state (passed, failed, or error). The result field is populated on terminal states.

Authentication

AuthorizationBearer

Enter the key with the Bearer prefix, e.g. ‘Bearer API_KEY|ACCESS_TOKEN’.

Path parameters

idstringRequired

Response

The test run.

idstring

test_idstring

agent_idstring

statusenum

Lifecycle of a test run: queued - running - terminal.

Terminal states:

passed - the agent behaviour met the success criteria.
failed - the agent behaviour did not meet the success criteria.
error - the runner itself could not complete (LLM outage, network error, etc.), distinct from failed which means the agent behaviour was judged and found lacking.

Allowed values:

created_atdatetime

started_atdatetime or null

completed_atdatetime or null

resultobject or null

Populated on terminal status only.

errorstring

Human-readable error message when status is error.