> ## Documentation Index
> Fetch the complete documentation index at: https://docs.videodb.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Describe Video Scene

> Generate AI description of a video scene

Generate an AI-powered description of a video scene's visual content.

<CodeGroup>
  ```python Python theme={null}
  import videodb

  conn = videodb.connect(api_key="your_api_key")
  coll = conn.get_collection()
  video = coll.get_videos()[0]

  # Get scene collection
  scene_collection = video.get_scene_collection("scene_collection_id")

  # Describe a specific scene
  scene = scene_collection.scenes[0]
  description = scene.describe()

  print(f"Scene description: {description}")

  # Describe with custom prompt
  custom_desc = scene.describe(prompt="Focus on people and their actions")

  # Describe with custom model configuration
  description = scene.describe(
      prompt="Describe this scene in detail",
      model_config={"model_name": "pro", "temperature": 0.5}
  )
  ```

  ```javascript Node.js theme={null}
  import { connect } from 'videodb';

  const conn = connect({ apiKey: 'your_api_key' });
  const coll = await conn.getCollection();
  const videos = await coll.getVideos();
  const video = videos[0];

  // Get scene collection
  const sceneCollection = await video.getSceneCollection('scene_collection_id');

  // Describe a specific scene
  const scene = sceneCollection.scenes[0];
  const description = await scene.describe();

  console.log(`Scene description: ${description}`);

  // Describe with custom prompt
  const customDesc = await scene.describe({ prompt: 'Focus on people and their actions' });

  // Describe with custom model configuration
  const detailed = await scene.describe({
      prompt: 'Describe this scene in detail',
      modelConfig: { modelName: 'pro', temperature: 0.5 }
  });
  ```
</CodeGroup>

<Note>
  * Generates description using AI vision models
  * Can use custom prompts to guide description focus
  * Optional `model_config` dict accepts `model_name` (e.g., `"pro"`) and `temperature` (0.0-1.0) to control the vision model
  * Overwrites existing scene description
  * Requires scene to be part of extracted scene collection
  * Scene IDs start with `sc-` prefix
</Note>


## OpenAPI

````yaml POST /video/{video_id}/scene/{scene_id}/describe/
openapi: 3.0.3
info:
  title: VideoDB Server API
  description: >
    VideoDB Server API for video, audio, and image processing with AI
    capabilities.

    This API provides comprehensive video management, search, indexing, and
    AI-powered features.
  version: 1.0.0
  contact:
    name: VideoDB Support
    url: https://videodb.io
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
servers:
  - url: https://api.videodb.io
    description: Production server
  - url: https://staging-api.videodb.io
    description: Staging server
security:
  - ApiKeyAuth: []
tags:
  - name: Authentication
    description: User authentication and API key management
  - name: Collections
    description: Collection management operations
  - name: Videos
    description: Video upload, processing, and management
  - name: Audio
    description: Audio management operations
  - name: Images
    description: Image management operations
  - name: Search
    description: Content search and indexing
  - name: AI Generation
    description: AI-powered content generation
  - name: Billing
    description: Billing and usage management
  - name: RTStream
    description: Real-time streaming operations
  - name: Utilities
    description: Utility endpoints
  - name: Meeting
    description: Meeting recording and management
  - name: Capture
    description: Capture session management for recording streams
  - name: Editor
    description: Timeline editor operations
  - name: Transcode
    description: Media transcoding operations
  - name: Assets
    description: Cross-collection asset listing
paths:
  /video/{video_id}/scene/{scene_id}/describe/:
    post:
      summary: Describe video scene
      parameters:
        - name: video_id
          in: path
          required: true
          schema:
            type: string
            pattern: ^m-
            example: m-12345
        - name: scene_id
          in: path
          required: true
          schema:
            type: string
            example: scene-123
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                prompt:
                  type: string
                  example: Describe what happens in this scene
                model_name:
                  type: string
                  example: gpt-4
      responses:
        '200':
          description: Scene description generated
          content:
            application/json:
              schema:
                type: object
                properties:
                  success:
                    type: boolean
                    example: true
                  data:
                    type: object
                    properties:
                      description:
                        type: string
                        example: Scene description text
      security:
        - ApiKeyAuth: []
components:
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-access-token
      description: API key for authentication (sk-xxx format)

````