`recordings_retranscribe`

Re-transcribe & re-diarize a recording

Re-run transcription + speaker diarization (pyannote) on an EXISTING recording. Use to recover speaker labels when a recording shows everyone as one unnamed speaker (all one color) — e.g. it was transcribed before diarization was working. This REPLACES the transcript (re-runs speech-to-text + diarization + speaker identity + auto-title) and UNLINKS any existing clips, so only use it on a recording without clips worth keeping. Returns immediately with status "transcribing"; poll the recording (recordings_list) to see the labeled speakers when it finishes.

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_retranscribe",
  "title": "Re-transcribe & re-diarize a recording",
  "description": "Re-run transcription + speaker diarization (pyannote) on an EXISTING recording. Use to recover speaker labels when a recording shows everyone as one unnamed speaker (all one color) — e.g. it was transcribed before diarization was working. This REPLACES the transcript (re-runs speech-to-text + diarization + speaker identity + auto-title) and UNLINKS any existing clips, so only use it on a recording without clips worth keeping. Returns immediately with status \"transcribing\"; poll the recording (recordings_list) to see the labeled speakers when it finishes.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string",
        "description": "The recording public ID to re-transcribe and re-diarize."
      }
    },
    "required": [
      "recording_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": true,
    "idempotentHint": false,
    "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"
      },
      "status": {
        "type": "string",
        "description": "\"transcribing\" once the job is queued."
      }
    },
    "required": [],
    "additionalProperties": false
  }
}

Errors

[
  "recording_not_found",
  "billing_required",
  "invalid_input"
]

Examples

[]