50 free credits · no card

TikTok Transcript API, every video in one call.

Q: What happens when a clip has no captions?

The audio is transcribed automatically on the same call: no second endpoint and no change to your code. TikTok clips are short, so this almost always returns inline rather than as a job. Transcription is billed by audio duration, one credit per started 5 minutes, and only on delivery, which for every clip under 5 minutes is a single credit.

Q: Which languages does it return?

Whatever caption track the clip carries, with the language stamped on the response. When none exists and the audio is transcribed, the language is detected automatically rather than assumed.

Q: What are the rate limits?

Per-plan request rates, returned on every response as standard rate-limit headers so a client can back off without guessing. Batch is the cheaper path for volume: one call carries up to 50 videos on the free tier, Basic and Pro, and up to 500 on Mega and Scale.

Q: Can I fetch many videos in one request?

Yes. POST /transcripts/batch takes up to 50 URLs per call, 500 on Mega and Scale, and returns a per-item outcome rather than failing the whole request. You are charged one credit per successfully delivered caption transcript; failures cost nothing.

Q: What is in the free tier?

50 credits a month, no card. Every endpoint is included, not a reduced subset, so you can build the real integration before deciding to pay for it.

Q: Is a credit the same as a request?

No. A credit is a delivered result. A caption transcript is one credit, a profile, playlist or search page is one credit, and polling a job, checking your balance and the health probe are free. Failed and empty results are never charged.

Q: Are there SDKs?

Python and JavaScript, both thin wrappers over the same REST endpoints with typed models. There is also an official n8n community node, and an MCP server if you would rather let an assistant make the call.

Q: What happens when TikTok changes something?

We fix it. Extraction runs through several methods behind one endpoint, so a change that breaks one path usually falls through to another before anyone notices, and the response shape your code parses does not move either way.

Clean text with timestamped segments, for any public video, whole profile, playlist or keyword search: over REST, an MCP server, or the Python and JavaScript SDKs.

Start with 50 free credits Read the docs

No card required. Failed fetches are free.

@dev · 0:47captions · en · 8 segments

00:00Everyone is sleeping on AI agents, and I think it is because the demos all look the same.

00:04They do not just answer questions the way a chatbot does, they actually go and do the work.

00:09So it fetches the data, cleans it up, writes the summary, and files it where it belongs.

00:16We tested this against a much bigger model last month and honestly the size barely mattered.

00:23What moved the numbers was retrieval, giving it the right source material at the right moment.

00:31Half our pipeline was video, interviews and clips like this one, and none of it was searchable.

00:38Once we turned all of that into text with timestamps, the accuracy problem mostly went away.

00:44Retrieval won on every benchmark we ran, and it was not close.

<2s
median caption fetch: 99.89%
API uptime: 500+
developers served: 3
Platforms covered

One call, one shape.

Send a TikTok URL. Below are two different clips: the first carries a caption track, the second has none and was transcribed from its audio. Same request, same fields, same parser. Only source tells them apart.

The request, either way

curl -X POST https://transcriptfetch.com/api/v2/transcripts/video \
  -H "Authorization: Bearer $TRANSCRIPTFETCH_KEY" \
  -d '{"video": "<any supported url>"}'

Clip with captions

{
  "ok": true,
  "data": {
    "kind": "transcript",
    "platform": "tiktok",
    "channel": "@dev",
    "duration": 47,
    "language": "en",
    "source": "captions",
    "segments": [
      { "start": 0, "duration": 4.1,
        "text": "Everyone is sleeping on AI agents" },
      … 7 more
    ]
  },
  "usage": { "credits_spent": 1, "balance": 49 }
}

200 · 1 credit

Clip with no captions

{
  "ok": true,
  "data": {
    "kind": "transcript",
    "platform": "tiktok",
    "channel": "@dev",
    "duration": 52,
    "language": "en",
    "source": "audio",
    "segments": [
      { "start": 0, "duration": 3.8,
        "text": "So the first thing to understand here" },
      … 9 more
    ]
  },
  "usage": { "credits_spent": 1, "balance": 48 }
}

200 · 1 credit · transcribed

Nothing in your code branches on which path ran. A caption fetch is a flat single credit; transcription is billed by audio duration, which at TikTok lengths is usually the same single credit and shows up in usage rather than in the shape. Every field, with types

Try it on a real video.

Paste any TikTok link and run it against the live API. No account, no key, no card: you get the same JSON your code would.

6 free transcripts a month, no account needed.

TikTok transcriptEnglish · timestamps · clean text

Beyond one video

Resolve a profile, playlist or search into a list, then transcribe what you want. Every row's url is accepted by the transcript and batch endpoints as-is. Costs are stamped on each tile.

POST/transcripts/video
Fetch a transcript
One video URL. Captions, or AI Fallback Transcription when there are none.
1 credit
POST/transcripts/batch
Batch fetch
Up to 50 URLs per call, 500 on Mega and Scale. Per-item outcomes.
1 credit per delivered
POST/transcripts/channel
List a profile
Latest posts from a TikTok profile, newest first, cursor-paged.
1 credit per page
POST/transcripts/playlist
List a playlist
Every video in a TikTok playlist, cursor-paged.
1 credit per page
POST/transcripts/search
Search videos
Keyword search, results ready to transcribe.
1 credit per page
GET/transcripts/jobs/{jobId}
Poll a job
State of an AI Fallback Transcription started by a 202.
Free
GET/me
Check balance
Validate the key and read remaining credits.
Free
GET/health
Health check
Public liveness probe for uptime monitoring.
Free

Three ways to connect

The same fetch, the same credit, whichever way you reach it. Write code, let an assistant call it, or run it from a workflow tool without writing any.

Call the endpoint

One POST with a TikTok URL, from any language. Typed SDKs for Python and Node if you want them, plain REST if you do not.

Read the API reference

Endpoint

POST /api/v2/transcripts/video

Let an assistant fetch it

Add the MCP server once and Claude, ChatGPT or Cursor pulls a transcript mid-conversation. OAuth on first use, nothing to deploy, no key to paste.

Set up MCP

Server URL

https://transcriptfetch.com/mcp

Run it in a workflow

The official n8n node, or an authenticated HTTP step in Make and Zapier. Fetch on a schedule, on a webhook, or whenever a row lands in a sheet.

See the n8n node

Community node

n8n-nodes-transcriptfetch

Works with

ChatGPT
Claude
Cursor
n8n
Make
Zapier

In your language

curl -X POST https://transcriptfetch.com/api/v2/transcripts/video \
  -H "Authorization: Bearer $TRANSCRIPTFETCH_KEY" \
  -H "Content-Type: application/json" \
  -d '{"video": "https://www.tiktok.com/@dev/video/7300000000000000000"}'

import os, requests

r = requests.post(
    "https://transcriptfetch.com/api/v2/transcripts/video",
    headers={"Authorization": f"Bearer {os.environ['TRANSCRIPTFETCH_KEY']}"},
    json={"video": "https://www.tiktok.com/@dev/video/7300000000000000000"},
)
data = r.json()["data"]

for seg in data["segments"]:
    print(seg["start"], seg["text"])

Or pip install transcriptfetch-sdk for typed models and async.

const res = await fetch(
  "https://transcriptfetch.com/api/v2/transcripts/video",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.TRANSCRIPTFETCH_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      video: "https://www.tiktok.com/@dev/video/7300000000000000000",
    }),
  },
);
const { data } = await res.json();

for (const seg of data.segments) {
  console.log(seg.start, seg.text);
}

Or npm i transcriptfetch for typed models and promises.

<?php
$ch = curl_init("https://transcriptfetch.com/api/v2/transcripts/video");
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_HTTPHEADER => [
        "Authorization: Bearer " . getenv("TRANSCRIPTFETCH_KEY"),
        "Content-Type: application/json",
    ],
    CURLOPT_POSTFIELDS => json_encode([
        "video" => "https://www.tiktok.com/@dev/video/7300000000000000000",
    ]),
]);
$data = json_decode(curl_exec($ch), true)["data"];

foreach ($data["segments"] as $seg) {
    echo $seg["start"], " ", $seg["text"], PHP_EOL;
}

Shared response

{
  "ok": true,
  "request_id": "req_…",
  "data": {
    "kind": "transcript",
    "video_id": "7300000000000000000",
    "platform": "tiktok",
    "channel": "@dev",
    "duration": 47,
    "language": "en",
    "source": "captions",
    "segments": [
      { "start": 0,   "duration": 4.1,
        "text": "Everyone is sleeping on AI agents" },
      { "start": 4.1, "duration": 5.2,
        "text": "They actually go and do the work" }
    ]
  },
  "usage": { "credits_spent": 1, "balance": 49 }
}

What people build with it

What claim did they make about retrieval?

get_transcript(video="…")

00:38Turning the video into timestamped text made the accuracy problem mostly go away.

AI apps and agents

Ground an assistant in what was actually said on camera. Segments carry start times, so an answer can cite the second rather than paraphrase a clip it never watched.

segments

00:09

00:23

00:38

chunked, cited, retrievable

Search and RAG indexing

Turn a creator's back catalogue into text your index can reach. Chunk on timestamps and every retrieved passage keeps a link back to the moment.

mentions · 12 weeks

Trend and hook analysis

Track a hook, a claim or a product mention across more clips than anyone can sit through, then query the text instead of the feed.

Pricing

One credit per delivered caption transcript. Failed or empty results are free. Unused credits roll over up to twice your monthly allowance.

How much will my volume cost?

10,000transcripts / month

50250,000

Best plan

Pro

You pay

$25 / mo

Per 1,000

$2.50

Choose Pro

Plan	Price	Credits / month	Per 1,000
Free	$0/mo	50	Free	Get started
Basic	$5/mo	1,000	$5.00	Start with Basic
ProPopular	$15/mo	7,500	$2.00	Go Pro
Mega	$45/mo	35,000	$1.30	Go Mega
Scale	$229/mo	250,000	$0.92	Scale up

Top-ups are billed at your plan's per-1,000 rate and never expire. AI Fallback Transcription is billed by audio duration rather than per transcript, which on TikTok lengths usually lands at one credit a clip. Full pricing

Two ways to get TikTok text

Compared by approach rather than by vendor, because the real choice is whether you want to own the infrastructure.

Capability	TranscriptFetch	Your own scraper plus speech-to-text
Type	REST, any language	Headless browser, proxies and an STT pipeline of your own
Setup	Get a key, make a request	Weeks of plumbing before the first transcript
No captions on the clip	AI Fallback Transcription, same endpoint	Your own transcription step to build and pay for
Blocks and rotation	Handled for you	Your IP, blocked at scale
Profiles, playlists, search	Built in, paginated	More parsers
Batch	Up to 50 per call	Your queue
Cost of a failure	Nothing	You pay for the compute either way
When TikTok changes	We fix it	You fix it, tonight

There is no official route to compare against here, and that is the point: neither the Display API nor creator tools expose transcript text for arbitrary public videos, so every path to the spoken words runs through the audio. captions when the clip carries them, the audio when it does not.

Questions people ask first

What happens when a clip has no captions?

The audio is transcribed automatically on the same call: no second endpoint and no change to your code. TikTok clips are short, so this almost always returns inline rather than as a job. Transcription is billed by audio duration, one credit per started 5 minutes, and only on delivery, which for every clip under 5 minutes is a single credit.

Which languages does it return?

Whatever caption track the clip carries, with the language stamped on the response. When none exists and the audio is transcribed, the language is detected automatically rather than assumed.

What are the rate limits?

Per-plan request rates, returned on every response as standard rate-limit headers so a client can back off without guessing. Batch is the cheaper path for volume: one call carries up to 50 videos on the free tier, Basic and Pro, and up to 500 on Mega and Scale.

Can I fetch many videos in one request?

Yes. POST /transcripts/batch takes up to 50 URLs per call, 500 on Mega and Scale, and returns a per-item outcome rather than failing the whole request. You are charged one credit per successfully delivered caption transcript; failures cost nothing.

What is in the free tier?

50 credits a month, no card. Every endpoint is included, not a reduced subset, so you can build the real integration before deciding to pay for it.

Is a credit the same as a request?

No. A credit is a delivered result. A caption transcript is one credit, a profile, playlist or search page is one credit, and polling a job, checking your balance and the health probe are free. Failed and empty results are never charged.

Are there SDKs?

Python and JavaScript, both thin wrappers over the same REST endpoints with typed models. There is also an official n8n community node, and an MCP server if you would rather let an assistant make the call.

What happens when TikTok changes something?

We fix it. Extraction runs through several methods behind one endpoint, so a change that breaks one path usually falls through to another before anyone notices, and the response shape your code parses does not move either way.

Guides

Put the spoken web to work

50 free credits a month. No card required. Failed fetches are never billed.

Start fetching Read the docs

TikTok Transcript API, every video in one call.

One call, one shape.

Try it on a real video.

Beyond one video

Fetch a transcript

Batch fetch

List a profile

List a playlist

Search videos

Poll a job

Check balance

Health check