Skip to main content
POST
/
video
/
{video_id}
/
scene
/
{scene_id}
/
describe
/
Describe video scene
curl --request POST \
  --url https://api.videodb.io/video/{video_id}/scene/{scene_id}/describe/ \
  --header 'Content-Type: application/json' \
  --header 'x-access-token: <api-key>' \
  --data '
{
  "prompt": "Describe what happens in this scene",
  "model_name": "gpt-4"
}
'
{
  "success": true,
  "data": {
    "description": "Scene description text"
  }
}
Generate an AI-powered description of a video scene’s visual content. 
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}
)
  • 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

Authorizations

​
x-access-token
string
header
required

API key for authentication (sk-xxx format)

Path Parameters

​
video_id
string
required
Pattern: ^m-
Example:

"m-12345"

​
scene_id
string
required
Example:

"scene-123"

Body

application/json
​
prompt
string
Example:

"Describe what happens in this scene"

​
model_name
string
Example:

"gpt-4"

Response

200 - application/json

Scene description generated

​
success
boolean
Example:

true

​
data
object