Documentation Index
Fetch the complete documentation index at: https://api-tools.memories.ai/llms.txt
Use this file to discover all available pages before exploring further.
Product: Visual Intelligence — Live Video Understanding
Use case: Apply a custom AI prompt continuously to a live RTMP stream (e.g. captioning, activity recognition, custom monitoring), results to your callback every 5s
Mode: Server-Pull (you give us an RTMP URL → we pull → results to your callback)
Host: https://stream.memories.ai
Auth: Authorization: sk-mavi-... (no Bearer prefix)
Stop an active live-stream understanding task started via Start Stream Video Understanding. Once stopped, no further callbacks will be sent, and resources are released.
If the RTMP source stops on its own or was never reachable when /streamConnect was called, the task terminates automatically — you don’t need to call this endpoint in that case.
Request Example
import requests
task_id = "5347085a-1747-4731-bdde-3856d09502c4"
url = f"https://stream.memories.ai/v1/understand/stop/{task_id}"
headers = {"Authorization": "sk-mavi-..."}
response = requests.post(url, headers=headers)
print(response.json())
Stop Stream Response
{
"status": 14,
"task_id": "5347085a-1747-4731-bdde-3856d09502c4"
}
Error Codes
| Code | Meaning |
|---|
-1 | Invalid request or task_id not found |
5000 | Internal server error |
The task ID returned when starting the stream
Stream stopped successfully
Example:"5347085a-1747-4731-bdde-3856d09502c4"