# Review voice test

Review a test-call transcript against the voice agent's instructions. Returns handled requests, gaps and suggested instruction changes.

POST https://api.brigg.app/v1/operations/voice.ReviewVoiceTest

## Access & visibility

Allow `voice.ReviewVoiceTest` on your API key.

**Acting member required.** Send `Brigg-Act-As` with an [approved member account ID](https://developer.brigg.app/authentication#member-delegation). The key supplies permissions; the member selects whose data is used.

The selected member must be active and approved by the credential. This selects whose private data is used; the credential supplies permissions. Private ownership and project boundaries still apply.

[Set up authentication](https://developer.brigg.app/authentication) · [Choose permissions](https://developer.brigg.app/permissions)

## Request fields

Send a JSON object with the following fields. Required fields must be included; omit optional fields you do not need.
| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `test_id` | string | Yes | Keep the returned test_id for this temporary session. Expired sessions require a new test. [voice.StartVoiceTest](https://developer.brigg.app/reference/voice/StartVoiceTest). At least 1 character. |
| `transcript` | array of [object](#request-transcript) | Yes | Complete caller/agent conversation to review in order. Brigg does not reconstruct it from previous RunVoiceTestTurn calls. At most 200 items. |

### request.transcript[]

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `role` | string | Yes | Conversation speaker: caller is the simulated customer; agent is the assistant. This is not a workspace permission or member role. Allowed: `"caller"`, `"agent"`. |
| `text` | string | Yes | The words spoken by this participant, in conversation order. At most 4000 characters. |

## Run a conversation test

Start a test for the intended inbox and retain its `test_id`. Text clients can use [Run voice test turn](https://developer.brigg.app/reference/voice/RunVoiceTestTurn); an audio connection URL is only needed for an audio client. Keep temporary connection URLs secret.

Pass the simulated caller's utterance and previous conversation history in order. Keep a stable `turn_id` for a retried turn. Review the returned reply and capability trace; a simulated response is not evidence that a real customer call succeeded. [Review voice test](https://developer.brigg.app/reference/voice/ReviewVoiceTest) accepts the conversation transcript for feedback. End the session when finished; an expired session needs a new start.

## Response

Returns **200 OK** with a JSON body.
| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `rows` | array of [ReviewVoiceTestRows](#reviewvoicetestrows-response-rows) | Yes | Generated feedback on the submitted transcript. Empty means no feedback was returned, including when generation could not produce a review; it is not a pass/fail certification. |

### ReviewVoiceTestRows · response.rows[]

| Field | Type | Required | Description |
| --- | --- | --- | --- |
| `status` | string | Yes | ok describes a handled instruction; gap identifies missing guidance. These are review findings, not the status of the voice test session. Allowed: `"ok"`, `"gap"`. |
| `text` | string | Yes | Text content. |
| `suggestion` | string | No | Suggested change to the assistant's instructions based on the review. |

## Errors & retries

Set `BRIGG_REQUEST_ID` once for each logical action. The samples send it as `Idempotency-Key`. Reuse the same value and body on retries, including after a timeout; a missing response does not prove the action failed.

For rate limits, follow the server’s retry guidance and back off. See [HTTP errors](https://developer.brigg.app/http#errors) and [safe retries and limits](https://developer.brigg.app/reliability).

| HTTP status | Code | What to do |
| --- | --- | --- |
| 400 | `invalid_json` | Send a JSON object with Content-Type: application/json. |
| 400 | `invalid_input` | Check the request fields and types. Supply a stable Idempotency-Key containing 1–200 characters. |
| 401 | `invalid_key` | The workspace API key is missing, invalid or revoked. |
| 403 | `forbidden` | Check the key’s operation and resource grants. Supply Brigg-Act-As with a member authorized by the key’s delegation grant. The selected member must be active and approved by the credential. This selects whose private data is used; the credential supplies permissions. Private ownership and project boundaries still apply. |
| 404 | `not_found` | The requested operation or resource is not available to this credential. |
| 429 | `rate_limited` | Wait for Retry-After before retrying. Reuse the original Idempotency-Key. |
| 403 | `voice_test_expired` | The test expired, is unknown, or belongs to another member. Start a new test under the intended approved member. |

## Next steps

- [Start voice test](https://developer.brigg.app/reference/voice/StartVoiceTest)
- [Run voice test turn](https://developer.brigg.app/reference/voice/RunVoiceTestTurn)
- [End voice test](https://developer.brigg.app/reference/voice/EndVoiceTest)

[Download OpenAPI](https://developer.brigg.app/openapi.json) · [Versioning & retirement](https://developer.brigg.app/versioning)

## Examples

### Example request

Fictional values. Replace IDs and business details with values from your workspace.
#### cURL


```sh
curl 'https://api.brigg.app/v1/operations/voice.ReviewVoiceTest' \
  -H "Authorization: Bearer $BRIGG_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Brigg-Act-As: $BRIGG_ACT_AS" \
  -H "Idempotency-Key: $BRIGG_REQUEST_ID" \
  --data-raw '{
  "test_id": "voice_test_kickoff",
  "transcript": [
    {
      "role": "caller",
      "text": "Discuss the pilot timeline and agree on next steps."
    }
  ]
}'
```

#### TypeScript


```typescript
const actAs = process.env.BRIGG_ACT_AS;
if (!actAs) throw new Error("Set BRIGG_ACT_AS to an approved member account ID.");

const requestId = process.env.BRIGG_REQUEST_ID;
if (!requestId) throw new Error("Set BRIGG_REQUEST_ID once per action and reuse it on retries.");

const response = await fetch("https://api.brigg.app/v1/operations/voice.ReviewVoiceTest", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.BRIGG_API_KEY}`,
    "Content-Type": "application/json",
    "Brigg-Act-As": actAs,
    "Idempotency-Key": requestId, // Create once per action; reuse on retries.
  },
  body: JSON.stringify({
    "test_id": "voice_test_kickoff",
    "transcript": [
      {
        "role": "caller",
        "text": "Discuss the pilot timeline and agree on next steps."
      }
    ]
  }),
});
const result = await response.json();
if (!response.ok) throw new Error(`${response.status}: ${result.error} — ${result.message}`);
console.log(result);
```

#### Python


```python
import json
import os
from urllib.request import Request, urlopen
from urllib.error import HTTPError

request_id = os.environ["BRIGG_REQUEST_ID"]  # Reuse for retries of this action.
payload = {
  "test_id": "voice_test_kickoff",
  "transcript": [
    {
      "role": "caller",
      "text": "Discuss the pilot timeline and agree on next steps."
    }
  ]
}
request = Request(
    "https://api.brigg.app/v1/operations/voice.ReviewVoiceTest",
    data=json.dumps(payload).encode("utf-8"),
    headers={
        "Authorization": f"Bearer {os.environ['BRIGG_API_KEY']}",
        "Content-Type": "application/json",
        "Brigg-Act-As": os.environ["BRIGG_ACT_AS"],
        "Idempotency-Key": request_id,  # Create once per action; reuse on retries.
    },
    method="POST",
)
try:
    with urlopen(request) as response:
        print(json.load(response))
except HTTPError as error:
    print(error.code, json.load(error))
    raise
```

#### Response example


```json
{
  "rows": [
    {
      "status": "ok",
      "text": "Discuss the pilot timeline and agree on next steps."
    }
  ]
}
```

## JSON schemas


```json-schema-request
{
  "type": "object",
  "properties": {
    "test_id": {
      "type": "string",
      "minLength": 1,
      "description": "Keep the returned test_id for this temporary session. Expired sessions require a new test. [voice.StartVoiceTest](https://developer.brigg.app/reference/voice/StartVoiceTest)."
    },
    "transcript": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "caller",
              "agent"
            ],
            "description": "Conversation speaker: caller is the simulated customer; agent is the assistant. This is not a workspace permission or member role."
          },
          "text": {
            "type": "string",
            "maxLength": 4000,
            "description": "The words spoken by this participant, in conversation order."
          }
        },
        "required": [
          "role",
          "text"
        ],
        "additionalProperties": false
      },
      "maxItems": 200,
      "description": "Complete caller/agent conversation to review in order. Brigg does not reconstruct it from previous RunVoiceTestTurn calls."
    }
  },
  "required": [
    "test_id",
    "transcript"
  ],
  "additionalProperties": false,
  "examples": [
    {
      "test_id": "voice_test_kickoff",
      "transcript": [
        {
          "role": "caller",
          "text": "Discuss the pilot timeline and agree on next steps."
        }
      ]
    }
  ]
}
```


```json-schema-response
{
  "type": "object",
  "properties": {
    "rows": {
      "type": "array",
      "items": {
        "title": "ReviewVoiceTestRows",
        "type": "object",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "ok",
              "gap"
            ],
            "description": "ok describes a handled instruction; gap identifies missing guidance. These are review findings, not the status of the voice test session."
          },
          "text": {
            "type": "string",
            "description": "Text content."
          },
          "suggestion": {
            "type": "string",
            "description": "Suggested change to the assistant's instructions based on the review."
          }
        },
        "required": [
          "status",
          "text"
        ],
        "additionalProperties": false
      },
      "description": "Generated feedback on the submitted transcript. Empty means no feedback was returned, including when generation could not produce a review; it is not a pass/fail certification."
    }
  },
  "required": [
    "rows"
  ],
  "additionalProperties": false,
  "examples": [
    {
      "rows": [
        {
          "status": "ok",
          "text": "Discuss the pilot timeline and agree on next steps."
        }
      ]
    }
  ]
}
```