Skip to main content

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 Search Use case: Upload videos and images, auto-index them, then search by natural language, image, or transcript phrase Host: https://api.memories.ai/serve/api/v1 Auth: Authorization: sk-mavi-... (no Bearer prefix)
Find video segments where a specific phrase was spoken in the public social-media library. Exact LIKE matching, not semantic — use it when you know the phrase verbatim. For semantic audio search use Search Public — by Text with search_type=BY_AUDIO.

​
Prerequisites

​
Request Example

import requests

headers = {"Authorization": "sk-mavi-..."}
params = {
    "query": "I don't know what is",
    "page": 1,
    "page_size": 100
}

response = requests.get(
    "https://api.memories.ai/serve/api/v1/search_public_audio_transcripts",
    headers=headers,
    params=params
)
print(response.json())

​
Parameters

​
query
string
required
Search phrase. LIKE-style exact matching against public transcripts.
​
page
integer
default:"1"
One-based page number. Must be greater than 0.
​
page_size
integer
default:"100"
Results per page. Range: 1 – 500.

​
Response

{
    "code": "0000",
    "msg": "success",
    "data": {
        "current_page": 1,
        "page_size": 100,
        "total_count": "5",
        "videos": [
            {
                "videoNo": "PI-600947902470296459",
                "videoName": "Sample public video title",
                "startTime": "23",
                "audio_ts": "... I don't know what is happening ...",
                "video_bucket": "mavi-public-video",
                "video_blob": "<scraper-id>.mp4"
            }
        ]
    },
    "success": true,
    "failed": false
}
​
data.current_page
integer
Page number returned.
​
data.page_size
integer
Page size returned.
​
data.total_count
string
Total matching segments across all pages, returned as a string (int(total_count) to use it).
​
data.videos[].videoNo
string
Public video identifier (typically prefixed with PI-).
​
data.videos[].videoName
string
Public video title or name.
​
data.videos[].startTime
string
Segment start time in seconds (returned as string).
​
data.videos[].audio_ts
string
The matched transcript text.
​
data.videos[].video_bucket
string
GCS bucket of our cached copy of the public video. Omitted when the storage location cannot be resolved.
​
data.videos[].video_blob
string
GCS blob (object) path of the cached video. Use it with video_bucket at GET /serve/api/v2/download?bucket=&blob= to fetch the file directly.

​
Notes & Limits

  • Rate limiting: Exceeding the per-account rate limit returns an error. See Rate limits.
  • Billing: Each successful call deducts credits from your account balance.