Speechbase: Universal Text-to-Speech Gateway & Voice Management

Records feedback for a generated speech request and returns a feedback ID. Omit `feedbackId` to start a new feedback timeline, or pass a previous `feedbackId` to append a later state under that same ID.

Records feedback for a generated speech request and returns a feedback ID. Omit feedbackId to start a new feedback timeline, or pass a previous feedbackId to append a later state under that same ID.

Authorization

bearerAuth

AuthorizationBearer <token>

API key

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

feedbackId?string

Omit to start a new feedback timeline, or pass a previous feedbackId to append a later state under the same ID.

Formatuuid

requestId*string

ID of the speech request this feedback is about, as returned by the generate endpoints.

Length1 <= length <= 128

score*integer

Quality rating from 0 to 100, higher is better. Send 0 or 100 for binary thumbs down or up, or any value in between for a graded score.

Range0 <= value <= 100

metric?string

Name of the metric this score measures. Defaults to 'quality'.

Default"quality"

Match^[A-Za-z0-9_.:-]+$

Length1 <= length <= 64

comment?string

Optional free-text comment from the end user.

Length1 <= length <= 1000

properties?

Optional map of scalar values used to group and filter feedback in the dashboard. The 'event' key records the interaction that produced this feedback and should be one of 'explicit_thumb_up' (end user marked the output good), 'explicit_thumb_down' (marked it bad), or 'same_text_regenerate' (end user re-ran the same input, an implicit negative signal). The 'reason' key is a short category for negative feedback, for example 'mispronunciation'. Any other keys are stored as-is and become group-by dimensions in the dashboard.

Default{}

metadata?

Optional opaque JSON blob stored with the feedback. Not queryable; use properties for anything you want to group or filter by.

Default{}

timestamp?string

When the feedback occurred, as an ISO 8601 timestamp. Defaults to the time the request is received.

Formatdate-time

Response Body

`application/json`

`application/problem+json`

curl -X POST "https://example.com/v1/feedback" \  -H "Authorization: Bearer $SPEECHBASE_API_KEY" \  -H "Content-Type: application/json" \  -d '{  "requestId": "string",  "score": 0}'

{
  "feedbackId": "8a5fb68c-aae2-438d-9a46-b4d8c8788e0b"
}

{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "validation": [
    {
      "path": [
        "string"
      ],
      "message": "string"
    }
  ],
  "provider": "string",
  "upstream_code": "string",
  "upstream_status": 0,
  "turn_index": 0
}

{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "validation": [
    {
      "path": [
        "string"
      ],
      "message": "string"
    }
  ],
  "provider": "string",
  "upstream_code": "string",
  "upstream_status": 0,
  "turn_index": 0
}

Submit speech feedback

Authorization

Request Body

Response Body

201application/json

400application/problem+json

401application/problem+json

`application/json`

`application/problem+json`

`application/problem+json`