Skip to main content
POST
Create video scene index
Create an AI-powered index of scenes in the video with descriptions, enabling visual search and scene understanding.
  • Analyzes video frames and creates AI descriptions for scenes
  • Supports shot-based and time-based extraction strategies
  • Can use custom prompts to guide scene description
  • Generates visual embeddings for semantic search
  • Returns scene index ID for later retrieval and searching
  • Extraction configuration controls frame sampling and scene detection

Open-weight model with Sandbox Compute

For open-weight VLM models, create a compatible sandbox first and pass sandbox_id with model_name.
VideoDB validates that the sandbox is active, belongs to your workspace/account, supports the requested model tier, and was created with a matching models or model_categories value when model selection was provided. See Sandbox Compute for sandbox setup.

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"

Body

application/json
scene_type
enum<string>
Available options:
shot,
time_based
Example:

"shot"

segmentation_threshold
number
Example:

0.8

callback_url
string
Example:

"https://webhook.example.com/callback"

Response

200 - application/json

Scene index creation started

success
boolean
Example:

true

status
enum<string>
Available options:
processing,
done,
failed
Example:

"processing"

data
object