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)
Retrieve the audio transcription (speech-to-text) of a video’s audio track. Each segment carries a time range and the transcribed text. For the visual scene descriptions, use Get Video Caption .
Prerequisites
You have created a memories.ai API key .
The video has been uploaded via the Upload API and finished parsing.
The source video has an audio track. Videos without audio return data: null even when the request succeeds.
Endpoint
GET /serve/api/v1/get_audio_transcription
Request Example
import requests
url = "https://api.memories.ai/serve/api/v1/get_audio_transcription"
headers = { "Authorization" : "sk-mavi-..." }
params = {
"video_no" : "VI605961375402668032" ,
"unique_id" : "default" ,
}
response = requests.get(url, headers = headers, params = params)
print (response.json())
Query Parameters
The video identifier returned by the upload API.
Namespace scoping the lookup to the account folder the video was uploaded under.
Response Example
Audio track present:
{
"code" : "0000" ,
"msg" : "success" ,
"data" : {
"videoNo" : "VI605961375402668032" ,
"transcriptions" : [
{
"index" : 0 ,
"content" : " I'm going to get my emergency and report." ,
"startTime" : "0" ,
"endTime" : "7"
},
{
"index" : 1 ,
"content" : " Mommy, you're going to go." ,
"startTime" : "7" ,
"endTime" : "12"
}
],
"createTime" : "1758276264066" ,
"video_bucket" : "mavi-resource" ,
"video_blob" : "VI605961375402668032.mp4"
},
"success" : true ,
"failed" : false
}
No audio track (or transcription not yet ready):
{
"code" : "0000" ,
"msg" : "success" ,
"data" : null ,
"success" : true ,
"failed" : false
}
Response Fields
Business status code. 0000 indicates success — including the “no audio track” case below.
Human-readable status message.
The transcription record, or null if the video has no audio track / no transcription has been produced. Check data is None explicitly rather than relying on the status code.
Echo of the requested video identifier.
Ordered list of transcription segments covering the audio track.
data.transcriptions[].index
Zero-based index of the segment.
data.transcriptions[].content
Transcribed text for this segment (often with a leading space).
data.transcriptions[].startTime
Segment start time in seconds, returned as a string.
data.transcriptions[].endTime
Segment end time in seconds, returned as a string.
Upload-time timestamp of the underlying video, in milliseconds since epoch, returned as a string.
GCS bucket of the underlying video file. Omitted when the storage location cannot be resolved.
GCS blob (object) path of the underlying video. Use it with video_bucket at GET /serve/api/v2/download?bucket=&blob= to fetch the file directly.
true when code == "0000" — true even on the “no audio track” path.
Notes & Limits
No-audio case is not an error : Videos without an audio track return code: "0000", success: true, data: null. Check for data explicitly.
Numeric strings : startTime, endTime, and createTime are strings — cast with int(...) before arithmetic.
Rate limiting : Subject to the standard Visual Search rate limits. See Rate limits .
The unique video ID returned by the upload API.
code
string integer string integer
data
object object[] string object object[] string