Instagram Video Caption
curl --request POST \
--url https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"video_url": "https://www.instagram.com/reels/DLlGZiCOBQ0/"
}
'import requests
url = "https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript"
payload = { "video_url": "https://www.instagram.com/reels/DLlGZiCOBQ0/" }
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({video_url: 'https://www.instagram.com/reels/DLlGZiCOBQ0/'})
};
fetch('https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'video_url' => 'https://www.instagram.com/reels/DLlGZiCOBQ0/'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript"
payload := strings.NewReader("{\n \"video_url\": \"https://www.instagram.com/reels/DLlGZiCOBQ0/\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"video_url\": \"https://www.instagram.com/reels/DLlGZiCOBQ0/\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"video_url\": \"https://www.instagram.com/reels/DLlGZiCOBQ0/\"\n}"
response = http.request(request)
puts response.read_body{
"code": 200,
"msg": "success",
"data": {
"task_id": "1cd78354af824c8eb1dafe4ed2435720"
},
"failed": false,
"success": true
}
{
"code": 200,
"message": "SUCCESS",
"data": {
"videoTranscript": {
"data": {
"data": [
{
"end_time": 9.0,
"start_time": 0.0,
"transcript": "A man with a tan, wearing a straw hat, sunglasses, black swim briefs, and lime green slides, stands on a sandy beach. He holds a red plastic cup in his left hand and gestures with his right hand as he speaks. The beach stretches behind him with distant trees and a few scattered people. He talks about having gastric bypass ten years ago and gaining some weight back."
},
{
"end_time": 15.0,
"start_time": 9.0,
"transcript": "The man continues to speak on the beach, holding the red cup. He gestures with his right hand as he explains his biggest goal is to go on Dancing with the Stars and perform."
},
{
"end_time": 22.0,
"start_time": 15.0,
"transcript": "The man on the beach, still in his straw hat and swim briefs, points his right index finger upwards and then gestures with his hands as he explains that he has the qualities and basics of what they look for in Dancing with the Stars."
}
],
"error_rate": 0.0,
"usage_metadata": {
"duration": 0.0,
"model": "gemini-2.5-flash",
"output_tokens": 813,
"prompt_tokens": 15160
}
},
"msg": "Video transcription completed successfully",
"success": true
},
"audioTranscript": {
"data": {
"data": [
{
"end_time": 2.44,
"speaker": null,
"start_time": 0.0,
"text": " I'm going to get a little personal."
},
{
"end_time": 6.4,
"speaker": null,
"start_time": 2.44,
"text": " I had gastric bypass 10 years ago."
},
{
"end_time": 8.16,
"speaker": null,
"start_time": 6.4,
"text": " I gained a little more."
}
],
"usage_metadata": {
"duration": 41.235782,
"model": "whisper-1",
"output_tokens": 0,
"prompt_tokens": 0
}
},
"msg": "ASR transcription completed successfully",
"success": true
}
},
"task_id": "8b4e80ea9774438c83b681dc427a310c"
}
Instagram
Instagram Video Caption
Get Instagram video caption.
POST
/
instagram
/
video
/
mai
/
transcript
Instagram Video Caption
curl --request POST \
--url https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"video_url": "https://www.instagram.com/reels/DLlGZiCOBQ0/"
}
'import requests
url = "https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript"
payload = { "video_url": "https://www.instagram.com/reels/DLlGZiCOBQ0/" }
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({video_url: 'https://www.instagram.com/reels/DLlGZiCOBQ0/'})
};
fetch('https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'video_url' => 'https://www.instagram.com/reels/DLlGZiCOBQ0/'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <api-key>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript"
payload := strings.NewReader("{\n \"video_url\": \"https://www.instagram.com/reels/DLlGZiCOBQ0/\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"video_url\": \"https://www.instagram.com/reels/DLlGZiCOBQ0/\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://mavi-backend.memories.ai/serve/api/v2/instagram/video/mai/transcript")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"video_url\": \"https://www.instagram.com/reels/DLlGZiCOBQ0/\"\n}"
response = http.request(request)
puts response.read_body{
"code": 200,
"msg": "success",
"data": {
"task_id": "1cd78354af824c8eb1dafe4ed2435720"
},
"failed": false,
"success": true
}
{
"code": 200,
"message": "SUCCESS",
"data": {
"videoTranscript": {
"data": {
"data": [
{
"end_time": 9.0,
"start_time": 0.0,
"transcript": "A man with a tan, wearing a straw hat, sunglasses, black swim briefs, and lime green slides, stands on a sandy beach. He holds a red plastic cup in his left hand and gestures with his right hand as he speaks. The beach stretches behind him with distant trees and a few scattered people. He talks about having gastric bypass ten years ago and gaining some weight back."
},
{
"end_time": 15.0,
"start_time": 9.0,
"transcript": "The man continues to speak on the beach, holding the red cup. He gestures with his right hand as he explains his biggest goal is to go on Dancing with the Stars and perform."
},
{
"end_time": 22.0,
"start_time": 15.0,
"transcript": "The man on the beach, still in his straw hat and swim briefs, points his right index finger upwards and then gestures with his hands as he explains that he has the qualities and basics of what they look for in Dancing with the Stars."
}
],
"error_rate": 0.0,
"usage_metadata": {
"duration": 0.0,
"model": "gemini-2.5-flash",
"output_tokens": 813,
"prompt_tokens": 15160
}
},
"msg": "Video transcription completed successfully",
"success": true
},
"audioTranscript": {
"data": {
"data": [
{
"end_time": 2.44,
"speaker": null,
"start_time": 0.0,
"text": " I'm going to get a little personal."
},
{
"end_time": 6.4,
"speaker": null,
"start_time": 2.44,
"text": " I had gastric bypass 10 years ago."
},
{
"end_time": 8.16,
"speaker": null,
"start_time": 6.4,
"text": " I gained a little more."
}
],
"usage_metadata": {
"duration": 41.235782,
"model": "whisper-1",
"output_tokens": 0,
"prompt_tokens": 0
}
},
"msg": "ASR transcription completed successfully",
"success": true
}
},
"task_id": "8b4e80ea9774438c83b681dc427a310c"
}
Product: Visual Intelligence — Social Media Scraping
Use case: Fetch video metadata, transcripts, captions, and comments from YouTube, Instagram, TikTok, and Twitter/X
Host:
https://mavi-backend.memories.ai/serve/api/v2
Auth: Authorization: sk-mavi-... (no Bearer prefix)Channel routing guide: see Social Media Scraping Overview. Endpoints with a
channel request field let you choose apify, rapid, or memories.ai; endpoints without this field use managed routing.Pricing: Base fee (0.01/video)+Inputtokens(0.45/1M) + Output tokens (3.75/1M)+Duration(0.0001/sec)
This is an asynchronous endpoint. It returns a Also accepts Reel URLs only —
task_id immediately. You must configure a Webhook to receive the processing results.If no webhook is configured on the account, the call is rejected at submit time with HTTP 400:{"code": 400, "msg": "An async request requires at least one webhook.", "data": null}
/p/<shortcode>/ post URLs fail validation, same as /instagram/video/metadata.Code Example
import requests
BASE_URL = "https://mavi-backend.memories.ai/serve/api/v2"
API_KEY = "sk-mavi-..."
HEADERS = {
"Authorization": f"{API_KEY}"
}
def instagram_video_caption(video_url: str):
url = f"{BASE_URL}/instagram/video/mai/transcript"
data = {"video_url": video_url}
resp = requests.post(url, headers=HEADERS, json=data)
return resp.json()
# Usage example
result = instagram_video_caption("https://www.instagram.com/reels/DLlGZiCOBQ0/")
print(result)
Response
Returns the caption task information.{
"code": 200,
"msg": "success",
"data": {
"task_id": "1cd78354af824c8eb1dafe4ed2435720"
},
"failed": false,
"success": true
}
{
"code": 200,
"message": "SUCCESS",
"data": {
"videoTranscript": {
"data": {
"data": [
{
"end_time": 9.0,
"start_time": 0.0,
"transcript": "A man with a tan, wearing a straw hat, sunglasses, black swim briefs, and lime green slides, stands on a sandy beach. He holds a red plastic cup in his left hand and gestures with his right hand as he speaks. The beach stretches behind him with distant trees and a few scattered people. He talks about having gastric bypass ten years ago and gaining some weight back."
},
{
"end_time": 15.0,
"start_time": 9.0,
"transcript": "The man continues to speak on the beach, holding the red cup. He gestures with his right hand as he explains his biggest goal is to go on Dancing with the Stars and perform."
},
{
"end_time": 22.0,
"start_time": 15.0,
"transcript": "The man on the beach, still in his straw hat and swim briefs, points his right index finger upwards and then gestures with his hands as he explains that he has the qualities and basics of what they look for in Dancing with the Stars."
}
],
"error_rate": 0.0,
"usage_metadata": {
"duration": 0.0,
"model": "gemini-2.5-flash",
"output_tokens": 813,
"prompt_tokens": 15160
}
},
"msg": "Video transcription completed successfully",
"success": true
},
"audioTranscript": {
"data": {
"data": [
{
"end_time": 2.44,
"speaker": null,
"start_time": 0.0,
"text": " I'm going to get a little personal."
},
{
"end_time": 6.4,
"speaker": null,
"start_time": 2.44,
"text": " I had gastric bypass 10 years ago."
},
{
"end_time": 8.16,
"speaker": null,
"start_time": 6.4,
"text": " I gained a little more."
}
],
"usage_metadata": {
"duration": 41.235782,
"model": "whisper-1",
"output_tokens": 0,
"prompt_tokens": 0
}
},
"msg": "ASR transcription completed successfully",
"success": true
}
},
"task_id": "8b4e80ea9774438c83b681dc427a310c"
}
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | string | Response code indicating the result status |
| msg | string | Response message describing the operation result |
| data | object | Response data object containing task information |
| data.task_id | string | Unique identifier of the caption task |
| success | boolean | Indicates whether the operation was successful |
| failed | boolean | Indicates whether the operation failed |
Callback Response Parameters
When the Instagram video caption generation is complete, a callback will be sent to your configured webhook URL.| Parameter | Type | Description |
|---|---|---|
| code | string | Response code (200 indicates success) |
| message | string | Status message (e.g., “SUCCESS”) |
| data | object | Response data object containing both video and audio transcription results |
| data.videoTranscript | object | Video transcription result object |
| data.videoTranscript.data | object | Inner data object containing video caption segments and usage information |
| data.videoTranscript.data.data | array | Array of video caption segments with timestamps |
| data.videoTranscript.data.data[].start_time | number | Start time of the video segment in seconds |
| data.videoTranscript.data.data[].end_time | number | End time of the video segment in seconds |
| data.videoTranscript.data.data[].transcript | string | Video transcription text describing the visual content |
| data.videoTranscript.data.error_rate | number | Error rate of the video caption (0.0 means no errors) |
| data.videoTranscript.data.usage_metadata | object | Usage statistics for the video caption |
| data.videoTranscript.data.usage_metadata.duration | number | Processing duration in seconds |
| data.videoTranscript.data.usage_metadata.model | string | The AI model used for video caption (e.g., “gemini-2.5-flash”) |
| data.videoTranscript.data.usage_metadata.output_tokens | integer | Number of tokens in the generated video caption |
| data.videoTranscript.data.usage_metadata.prompt_tokens | integer | Number of tokens in the input prompt |
| data.videoTranscript.msg | string | Detailed message about the video caption result |
| data.videoTranscript.success | boolean | Indicates whether the video caption was successful |
| data.audioTranscript | object | Audio transcription result object |
| data.audioTranscript.data | object | Inner data object containing audio transcription segments and usage information |
| data.audioTranscript.data.data | array | Array of audio transcription segments with timestamps |
| data.audioTranscript.data.data[].start_time | number | Start time of the audio segment in seconds |
| data.audioTranscript.data.data[].end_time | number | End time of the audio segment in seconds |
| data.audioTranscript.data.data[].text | string | Audio transcription text for this segment |
| data.audioTranscript.data.data[].speaker | string | null | Speaker identifier (null if speaker identification not enabled) |
| data.audioTranscript.data.usage_metadata | object | Usage statistics for the audio transcription |
| data.audioTranscript.data.usage_metadata.duration | number | Audio duration in seconds |
| data.audioTranscript.data.usage_metadata.model | string | The model used for audio transcription (e.g., “whisper-1”) |
| data.audioTranscript.data.usage_metadata.output_tokens | integer | Number of output tokens (0 for audio transcription) |
| data.audioTranscript.data.usage_metadata.prompt_tokens | integer | Number of prompt tokens (0 for audio transcription) |
| data.audioTranscript.msg | string | Detailed message about the audio transcription result |
| data.audioTranscript.success | boolean | Indicates whether the audio transcription was successful |
| task_id | string | The task ID associated with this transcription request |
Authorizations
Body
application/json
The Instagram video URL
Example:
"https://www.instagram.com/reels/DLlGZiCOBQ0/"
Response
200 - application/json
Transcription task information
Response code indicating the result status
Example:
200
Response message describing the operation result
Example:
"success"
Response data object containing task information
Show child attributes
Show child attributes
Indicates whether the operation was successful
Example:
true
Indicates whether the operation failed
Example:
false
⌘I
