Skip to main content
POST
/
rtstream
/
{stream_id}
/
index
/
scene
Create RTStream scene index
curl --request POST \
  --url https://api.videodb.io/rtstream/{stream_id}/index/scene \
  --header 'Content-Type: application/json' \
  --header 'x-access-token: <api-key>' \
  --data '
{
  "extraction_type": "time",
  "extraction_config": {
    "time": 10,
    "frame_count": 5
  },
  "prompt": "Describe the scene",
  "model_name": "GPT4o",
  "model_config": {},
  "name": "My Scene Index",
  "ws_connection_id": "conn-123"
}
'
{
  "success": true,
  "data": {
    "rtstream_index_id": "scene-idx-12345",
    "extraction_type": "time",
    "status": "running",
    "prompt": "Describe the scene",
    "name": "My Scene Index"
  }
}

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.

Create a scene index on a real-time stream for continuous visual analysis. The index extracts and describes scenes as the stream progresses.
  • extraction_type can be time or transcript
  • For time-based extraction, set extraction_config.time for interval in seconds
  • prompt defines what the model should look for in each scene
  • Use ws_connection_id to receive real-time index updates via WebSocket

List Scene Indexes

View all indexes on a stream

Search RTStream

Search indexed content

Authorizations

​
x-access-token
string
header
required

API key for authentication (sk-xxx format)

Path Parameters

​
stream_id
string
required
Example:

"rts-12345"

Body

application/json
​
extraction_type
enum<string>
default:time
Available options:
time,
transcript
Example:

"time"

​
extraction_config
object
​
prompt
string
Example:

"Describe the scene"

​
model_name
string
Example:

"GPT4o"

​
model_config
object
​
name
string
Example:

"My Scene Index"

​
ws_connection_id
string
Example:

"conn-123"

Response

200 - application/json

Scene index created

​
success
boolean
Example:

true

​
data
object