`recordings_get_speaker_evidence`

Get recording speaker evidence

Read the first-class speaker evidence for a recording. Returns one row per diarized speaker track, profile bindings, confirmation state, voiceprint/transcript/visual evidence, roles, bounded source-time subject geometry when a current evidence generation exists, summary counts, and a compact model context. Geometry is evidence, never an already-chosen crop or title placement.

Surface: App-only

Product release 1dce717408a55fac1047e7d779177fa3ef8ede51
Public contract commit 1ce47f7857ae3d9b6933fe83d5c33de3ae5efc64
Public contract SHA-256 241d47d25e4b4c1dae9d2263793874d06fc4ba7bc3c78d4cf2bc63fbb32ed7dc
Captured 2026-09-24T16:39:30.100Z. Review or improve this contract on GitHub.

These blocks show the complete MCP descriptors captured from serving Rails. Security schemes and resource URIs can differ by connected host.

App descriptor

{
  "name": "recordings_get_speaker_evidence",
  "title": "Get recording speaker evidence",
  "description": "Read the first-class speaker evidence for a recording. Returns one row per diarized speaker track, profile bindings, confirmation state, voiceprint/transcript/visual evidence, roles, bounded source-time subject geometry when a current evidence generation exists, summary counts, and a compact model context. Geometry is evidence, never an already-chosen crop or title placement.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string",
        "description": "Recording public ID."
      },
      "decision_id": {
        "type": "string",
        "description": "Optional saved identity answer on this Recording. Returns its support and current withdrawal scope."
      },
      "speaker_map_id": {
        "type": "string",
        "description": "Alternatively inspect the answer on this exact voice, including an older human confirmation."
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "visibility": [
        "app"
      ]
    },
    "openai/widgetAccessible": true,
    "openai/visibility": "private"
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string"
      },
      "identity_answer": {
        "type": "object",
        "description": "Selected answer, accessible source evidence, human dependency and withdrawal scope fingerprint."
      },
      "speaker_evidence": {
        "type": "object"
      },
      "speaker_model_context": {
        "type": "object"
      }
    },
    "required": [],
    "additionalProperties": false
  }
}

Errors

[
  "recording_not_found",
  "transcript_not_ready",
  "invalid_input"
]

Examples

[]