Video transcript

When to use this

Use it to turn a TikTok into text: repurpose a script, search what creators say, or feed it to an LLM. transcript is WEBVTT with timestamps (the same format other TikTok APIs return); text is the same words as plain text.

Transcripts come from TikTok's own captions: auto-generated speech captions (source: asr), the creator's own captions, or TikTok's translations. Most spoken videos have them. A video without captions (music only, or captions off) returns transcript: null with languages: [].

No captions? Pass use_ai_as_fallback=true and we transcribe the audio ourselves (source: ai) for videos up to 2 minutes. That costs 2 credits in total, and only when it runs; with captions it's still 1. If it hears no speech (music only), you get 404 transcript_unavailable at the base price, and that answer is cached.

By default you get the original language. Pass language (e.g. es) to pick one of languages.

Deleted, private and region-locked videos return 404 not_found.

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/v1/tiktok/video/transcript?url=https%3A%2F%2Fwww.tiktok.com%2F%40hubspot%2Fvideo%2F7671325437229845774" \
  -H "x-api-key: YOUR_API_KEY"

const params = new URLSearchParams({
  url: "https://www.tiktok.com/@hubspot/video/7671325437229845774",
});
const res = await fetch(`https://api.lurkapi.com/v1/tiktok/video/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.text);

import os
import requests

res = requests.get(
    "https://api.lurkapi.com/v1/tiktok/video/transcript",
    params={
        "url": "https://www.tiktok.com/@hubspot/video/7671325437229845774",
    },
    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["text"])

package main

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

func main() {
	params := url.Values{}
	params.Set("url", "https://www.tiktok.com/@hubspot/video/7671325437229845774")
	req, _ := http.NewRequest("GET", "https://api.lurkapi.com/v1/tiktok/video/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"]))
	}
	fmt.Println(data["text"])
}

<?php
$params = http_build_query([
    'url' => 'https://www.tiktok.com/@hubspot/video/7671325437229845774',
]);
$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/v1/tiktok/video/transcript?' . $params, false, $context);
$data = json_decode($body, true);
if (!$data['success']) {
    throw new Exception("{$data['code']}: {$data['error']}");
}
print_r($data['text']);

require 'json'
require 'net/http'

uri = URI('https://api.lurkapi.com/v1/tiktok/video/transcript')
uri.query = URI.encode_www_form(
  'url' => 'https://www.tiktok.com/@hubspot/video/7671325437229845774',
)
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 data['text']

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": 99983,
  "credits_charged": 1,
  "id": "7671325437229845774",
  "url": "https://www.tiktok.com/@hubspot/video/7671325437229845774",
  "languages": [
    {
      "language": "en",
      "source": "asr"
    }
  ],
  "transcript": "WEBVTT\n\n\n00:00:00.060 --> 00:00:02.400\nWhen your lead score came across …",
  "text": "When your lead score came across the threshold,\nI knew there was potenti…",
  "language": "en",
  "source": "asr"
}

Response fields

Every field in a successful response, and what it means. A name with [] belongs to each item of a list: languages[].language is the language of every item in languages. 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 tiktok_transcript tool. For example:

Use LurkAPI's tiktok_transcript tool with url "https://www.tiktok.com/@hubspot/video/7671325437229845774", then summarize what you find.

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

{"url": "https://www.tiktok.com/@hubspot/video/7671325437229845774"}

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.