# transcript_words_window

Canonical HTML page: https://bitterclip.com/docs/assistants/tools/transcript_words_window

Surface: app-only

Product release: 185ad8f4adfa21ae055b5bd6f97968d9044480d1
Public contract commit: d2ab41fab4088c07c0f6b924fa4f3c63481b936a
Public contract SHA-256: 2365c73c2aef7b9f85e8434d8e29ea29f40824bc3a46a72a356155ea328757fc
Descriptor SHA-256: ef560141873b318181e4a3e6c2c93c1bbe9d49fc3c3fd417cce2e079ef1c4bee
Captured: 2026-10-29T03:35:56.855Z
Source: https://app.bitterclip.com/api/v1/mcp_descriptors.json

App/internal read-only semantic locator for a small set of transcript lines on a RAW recording (the drawer, not an episode). Word annotations are approximate and never authorize a structural cut; episode editing locates candidate media with episode_read and places precise boundaries from episode_zoom or episode_sample_frames evidence.

The JSON blocks below are the exact MCP descriptor projections served by Rails for the named profiles at capture time. Security schemes and resource URIs may vary by connected host.

## App descriptor

```json
{
  "name": "transcript_words_window",
  "title": "Read approximate word annotations for transcript lines",
  "description": "App/internal read-only semantic locator for a small set of transcript lines on a RAW recording (the drawer, not an episode). Word annotations are approximate and never authorize a structural cut; episode editing locates candidate media with episode_read and places precise boundaries from episode_zoom or episode_sample_frames evidence.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "recording_id": {
        "type": "string",
        "description": "The recording public ID whose transcript lines to inspect."
      },
      "line_numbers": {
        "type": "array",
        "description": "Specific transcript line numbers to inspect, such as [31, 33].",
        "items": {
          "type": "integer"
        }
      },
      "start_line": {
        "type": "integer",
        "description": "First line in an inclusive contiguous range."
      },
      "end_line": {
        "type": "integer",
        "description": "Last line in an inclusive contiguous range. Defaults to start_line when omitted by internal callers."
      },
      "transcript_fingerprint": {
        "type": "string",
        "description": "Required fingerprint for the recording's current line segmentation; prevents stale line numbers after retranscription or speaker-label changes."
      },
      "segmentation_version": {
        "type": "string",
        "description": "Optional segmentation version for the recording's current line segmentation."
      }
    },
    "required": [
      "recording_id",
      "transcript_fingerprint"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "title": "Read approximate word annotations for transcript lines",
    "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"
      },
      "segmentation_version": {
        "type": "string"
      },
      "transcript_fingerprint": {
        "type": "string"
      },
      "line_count": {
        "type": "integer"
      },
      "transcript": {
        "type": "string",
        "description": "Plain text timing for the requested line(s). Word-timed transcripts include word_id values for semantic anchors and local timing reference; unit fallback rows are line-selection only."
      }
    },
    "required": [],
    "additionalProperties": false
  }
}
```

## Errors

```json
[
  "recording_not_found",
  "transcript_not_ready",
  "invalid_input"
]
```

## Examples

```json
[]
```
