Media transcript

When to use this

Use it to get what's said in a reel as text. Pass a public reel or video URL; it works on videos up to 120 seconds. For a carousel, its first video is transcribed. The post's author, caption and preview image come with the transcript.

A new transcript costs 2 credits when speech-to-text succeeds. One we already have costs 1, since speech-to-text doesn't run again. A video with no audio or no speech returns 404 transcript_unavailable at the base price. (Instagram mutes reels whose song was removed.)

Photos, private posts, videos over 120 seconds and videos whose length Instagram doesn't give can't be transcribed. The transcript is machine-made and can contain mistakes.

Example request

Copy one and replace YOUR_API_KEY with your API key (get one free). The code versions read the key from the LURKAPI_API_KEY environment variable instead.

curl "https://api.lurkapi.com/v2/instagram/media/transcript?url=https%3A%2F%2Fwww.instagram.com%2Freel%2FDdl5eH-u4le%2F" \
  -H "x-api-key: YOUR_API_KEY"

const params = new URLSearchParams({
  url: "https://www.instagram.com/reel/Ddl5eH-u4le/",
});
const res = await fetch(`https://api.lurkapi.com/v2/instagram/media/transcript?${params}`, {
  headers: { "x-api-key": process.env.LURKAPI_API_KEY },
});
const data = await res.json();
if (!data.success) throw new Error(`${data.code}: ${data.error}`);
console.log(data.segments);

import os
import requests

res = requests.get(
    "https://api.lurkapi.com/v2/instagram/media/transcript",
    params={
        "url": "https://www.instagram.com/reel/Ddl5eH-u4le/",
    },
    headers={"x-api-key": os.environ["LURKAPI_API_KEY"]},
    timeout=60,
)
data = res.json()
if not data["success"]:
    raise RuntimeError(f"{data['code']}: {data['error']}")
print(data["segments"])

package main

import (
	"encoding/json"
	"fmt"
	"net/http"
	"net/url"
	"os"
	"time"
)

func main() {
	params := url.Values{}
	params.Set("url", "https://www.instagram.com/reel/Ddl5eH-u4le/")
	req, _ := http.NewRequest("GET", "https://api.lurkapi.com/v2/instagram/media/transcript?"+params.Encode(), nil)
	req.Header.Set("x-api-key", os.Getenv("LURKAPI_API_KEY"))

	client := &http.Client{Timeout: 60 * time.Second}
	res, err := client.Do(req)
	if err != nil {
		panic(err)
	}
	defer res.Body.Close()

	var data map[string]any
	if err := json.NewDecoder(res.Body).Decode(&data); err != nil {
		panic(err)
	}
	if data["success"] != true {
		panic(fmt.Sprintf("%v: %v", data["code"], data["error"]))
	}
	out, _ := json.MarshalIndent(data["segments"], "", "  ")
	fmt.Println(string(out))
}

<?php
$params = http_build_query([
    'url' => 'https://www.instagram.com/reel/Ddl5eH-u4le/',
]);
$context = stream_context_create(['http' => [
    'header' => 'x-api-key: ' . getenv('LURKAPI_API_KEY'),
    'timeout' => 60,
    'ignore_errors' => true,
]]);
$body = file_get_contents('https://api.lurkapi.com/v2/instagram/media/transcript?' . $params, false, $context);
$data = json_decode($body, true);
if (!$data['success']) {
    throw new Exception("{$data['code']}: {$data['error']}");
}
print_r($data['segments']);

require 'json'
require 'net/http'

uri = URI('https://api.lurkapi.com/v2/instagram/media/transcript')
uri.query = URI.encode_www_form(
  'url' => 'https://www.instagram.com/reel/Ddl5eH-u4le/',
)
req = Net::HTTP::Get.new(uri)
req['x-api-key'] = ENV.fetch('LURKAPI_API_KEY')
res = Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme == 'https', read_timeout: 60) do |http|
  http.request(req)
end
data = JSON.parse(res.body)
raise "#{data['code']}: #{data['error']}" unless data['success']
puts JSON.pretty_generate(data['segments'])

Parameters

Add them to the URL after a ?. Join several with &.

Example response

A real response, captured from the live API. Lists are trimmed to a couple of items, and long text such as media links is cut short with ….

{
  "success": true,
  "credits_remaining": 999971,
  "credits_charged": 2,
  "code": "Ddl5eH-u4le",
  "url": "https://www.instagram.com/p/Ddl5eH-u4le/",
  "transcript": "Caitlin Clark is just a normal girl from Iowa, raised to do normal stuff…",
  "source": "speech_to_text",
  "language": "en",
  "duration_s": 30.0248125,
  "segments": [
    {
      "start": 0.3,
      "end": 4.92,
      "text": "Caitlin Clark is just a normal girl from Iowa, raised to do normal stuff."
    },
    {
      "start": 5.12,
      "end": 9.22,
      "text": "Cereal for breakfast, football on Sundays, golf on her days off."
    },
    {
      "start": 9.46,
      "end": 11.72,
      "text": "Eventually, she grew up and got a job."
    },
    {
      "start": 11.94,
      "end": 20.48,
      "text": "At this job, she sells out a variety of arenas, shoots from distances pr…"
    },
    {
      "start": 20.72,
      "end": 25.84,
      "text": "The media finds all of this extremely interesting, but to her, this is all totally normal."
    },
    {
      "start": 26.62,
      "end": 28.26,
      "text": "Nothing special to see here."
    }
  ],
  "user": {
    "pk": "13460080",
    "username": "nike",
    "full_name": "Nike",
    "profile_pic_url": "https://scontent-iad3-1.cdninstagram.com/v/t51.82787-19/551608484_185671…",
    "is_verified": true
  },
  "caption": "*Just a normal day for @caitlinclark22.\n\nWake up. Eat cereal. Lace up th…",
  "taken_at": 1790085604,
  "display_url": "https://scontent-iad6-1.cdninstagram.com/v/t51.82787-15/809201733_186664…"
}

Response fields

Every field in a successful response, and what it means. A name with [] belongs to each item of a list: segments[].start is the start of every item in segments. null means there's no value.

Cost and freshness

Each call costs 1 credit; 2 if speech-to-text runs. Calls turned away before they reach the platform (invalid parameters, a key or balance problem, a rate limit) are free, and so are 5xx errors. A not_found is charged, since the platform was checked. How charging works.

Answers are cached for up to 30 days. A repeat call within that time can return the same data, and costs the same.

Errors

A failed call returns success: false, an error message, a code your program can check, and a docs link. These are the errors this endpoint can return. All error codes.

Use it in Claude

Connect LurkAPI to Claude and ask in plain English. This endpoint is the instagram_media_transcript tool. For example:

Use LurkAPI's instagram_media_transcript tool with url "https://www.instagram.com/reel/Ddl5eH-u4le/", then summarize what you find.

Claude calls instagram_media_transcript with arguments like these, and each call costs 1 credit; 2 if speech-to-text runs:

{"url": "https://www.instagram.com/reel/Ddl5eH-u4le/"}

To save tokens, tool results leave out empty fields, keep one URL per image or video, and give transcripts as plain text unless you pass timestamps=true. A result over 45,000 characters comes in parts. Its _note gives the offset for the next part, and later parts are free for 15 minutes. Pass trim=false for the full response.