# How to get a TikTok video transcript 2 endpoints do it: TikTok user videos → TikTok video transcript. The worked example below is 11 calls and costs $0.0220 in all; a failed call is not charged. You get what is said in a TikTok video as text: the whole transcript and timed segments, for one video by its link or for every video of an account. ## Step by step ### Step 1: TikTok user videos For a whole account, list its videos by handle, 10 a page, newest first (`sort=popular` for the most popular). The next step takes each item's `id`. For one video you already have, go straight to the next step. ([TikTok user videos](https://dataxapi.com/apis/tiktok/users/videos/list/), $0.0020 / a call) cURL ```bash curl -G "https://api.dataxapi.com/v1/tiktok/users/videos/list" \ --data-urlencode "username=nasa" \ -H "Authorization: Bearer $DATAXAPI_API_KEY" ``` Python ```python from dataxapi import DataXAPI dx = DataXAPI() # reads DATAXAPI_API_KEY result = dx.tiktok.users.videos.list(username="nasa") print(result["data"]["items"]) ``` TypeScript ```typescript import { DataXAPI } from "@dataxapi/sdk"; const dx = new DataXAPI(); // reads DATAXAPI_API_KEY const result = await dx.tiktok.users.videos.list({ username: "nasa" }); console.log(result.data.items); ``` CLI ```bash dataxapi call tiktok.users.videos.list username=nasa ``` Recorded response: From a response recorded 2026-10-12 18:45 UTC. Names, text and IDs are examples, and so are the links: none is the recorded one (the page shows no one's personal data); the figures are as recorded. Long lists are cut. The request ID, cursor and balance are made up. ```jsonc { "code": "ok", "request_id": "a42fa228-bf2c-4880-b287-caceb8e1bd8d", "data": { "items": [ { "id": "7233742999990560590", "url": "https://www.tiktok.com/@hannah.w.photo/video/7233742999990560590", "type": "video", "text": "Everything I wish I knew about weekend hiking before starting.", "lang": "en", "published_at": "2026-07-21T20:09:02.000Z", "author": { "id": "6149684490433647203", "username": "hannah.w.photo", "name": "Hannah Weiss", "avatar_url": "https://p16-sign-va.tiktokcdn.com/tos-maliva-avt-0068/2ab492d722b3543fc068~c5_100x100.jpeg", "followers": 2060928 }, "metrics": { "likes": 103312, "comments": 3021, "shares": 3253, "favorites": 7513, "views": 1592522 }, "hashtags": [], "mentions": [], "is_pinned": true }, // … 9 more ] }, "page": { "next_cursor": "c1.yvxWofpiS46rHbSlVZq6wOmvvAKYGTTSKnC13UaD", "cursor_expires_at": "2026-10-12T19:45:11.000Z", "has_more": true, "returned": 10 }, "warnings": [], "meta": { "capability": "tiktok.users.videos.list", "result_status": "complete", "fetched_at": "2026-10-12T18:45:11.000Z", "cached": false, "replayed": false, "unavailable": { "title": "platform", "images": "capability", "author.verified": "capability", "metrics.reposts": "capability", "mentions.username": "capability", "mentions.name": "capability", "post_id": "platform", "parent_id": "platform", "root_id": "platform" }, "billing": { "amount": "0.002", "currency": "USD", "balance_after": "9.998" } } } ``` ### Step 2: TikTok video transcript Get the transcript by the video's `id`, or by its link as `url`. `text` is the whole transcript; `segments` gives it line by line, with `start` and `end` in seconds. ([TikTok video transcript](https://dataxapi.com/apis/tiktok/videos/transcript/get/), $0.0020 / a call) cURL ```bash curl -G "https://api.dataxapi.com/v1/tiktok/videos/transcript/get" \ --data-urlencode "id=7665840565958872333" \ -H "Authorization: Bearer $DATAXAPI_API_KEY" ``` Python ```python from dataxapi import DataXAPI dx = DataXAPI() # reads DATAXAPI_API_KEY result = dx.tiktok.videos.transcript.get(id="7665840565958872333") print(result["data"]["item"]) ``` TypeScript ```typescript import { DataXAPI } from "@dataxapi/sdk"; const dx = new DataXAPI(); // reads DATAXAPI_API_KEY const result = await dx.tiktok.videos.transcript.get({ id: "7665840565958872333" }); console.log(result.data.item); ``` CLI ```bash dataxapi call tiktok.videos.transcript.get id=7665840565958872333 ``` Recorded response: From a response recorded 2026-10-12 18:47 UTC. Names, text and IDs are examples, and so are the links: none is the recorded one (the page shows no one's personal data); the figures are as recorded. Long lists are cut. The request ID, cursor and balance are made up. ```jsonc { "code": "ok", "request_id": "d769ec30-ee48-492d-a245-185caeb7e795", "data": { "item": { "post_id": "7735791757913201402", "text": "Hey everyone, today I am going through what I packed for weekend hiking. Short version: light, fits in one bag, hard to break. Let's go piece by piece.", "segments": [ { "start": 1.14, "end": 2.76, "text": "Hey everyone, today I am going through what I packed for weekend hiking." }, { "start": 3.06, "end": 4.98, "text": "Short version: light, fits in one bag, hard to break." }, // … 35 more ] } }, "warnings": [], "meta": { "capability": "tiktok.videos.transcript.get", "result_status": "complete", "fetched_at": "2026-10-12T18:47:26.000Z", "cached": false, "replayed": false, "unavailable": { "lang": "capability" }, "billing": { "amount": "0.002", "currency": "USD", "balance_after": "9.998" } } } ``` ## What the example costs one page of an account's videos, then the transcript of each of those 10 videos | Endpoint | Calls | Price | Subtotal | | --- | --- | --- | --- | | [TikTok user videos](https://dataxapi.com/apis/tiktok/users/videos/list/) | 1 | $0.0020 | $0.0020 | | [TikTok video transcript](https://dataxapi.com/apis/tiktok/videos/transcript/get/) | 10 | $0.0020 | $0.0200 | | Total | 11 | | $0.0220 | Prices are the prices in force when this page was built. A failed call, and an object that does not exist, cost nothing. ## In your AI (MCP) Connect DataXAPI to your AI client once. Then say what you want; the agent finds these endpoints, checks the price and calls them on your balance. Say: Use DataXAPI to get the transcripts of the 10 latest videos of the TikTok account @nasa, and sum up each in one sentence. What the agent sends to the call tool: ```json { "capability": "tiktok.users.videos.list", "username": "nasa", "idempotency_key": "" } ``` [About the MCP server](https://dataxapi.com/mcp/) ## With a Skill The Videos to text Skill does this job as a ready-made task, under a spending cap. “What does this video say?” Its example run: 1 call, at most $0.0020. [Videos to text](https://dataxapi.com/skills/transcripts/) ## Good to know - Only a video TikTok has captions for has a transcript, and many have none. Such a video is answered `not_found` and is not charged, so the bill above is the most this can cost. A video that does not exist is answered the same way. - The answer does not say which language the transcript is in: `lang` is not returned. - The account's video list gives 10 a page; a cursor works for an hour, and an empty page is charged. - The transcript is the words only. A summary or a translation is for your own AI to write from `text`. ## Endpoints - [TikTok user videos](https://dataxapi.com/apis/tiktok/users/videos/list/) - [TikTok video transcript](https://dataxapi.com/apis/tiktok/videos/transcript/get/) ## More about TikTok - [TikTok API](https://dataxapi.com/apis/tiktok/) - [How to get TikTok comments with Python](https://dataxapi.com/guides/tiktok-comments-python/) - [How to search TikTok Shop products and read their reviews](https://dataxapi.com/guides/tiktok-shop-product-reviews/) - [Can ChatGPT read TikTok?](https://dataxapi.com/answers/can-chatgpt-read-tiktok/) --- Catalog revision c48ce454ae6c4c65. [HTML version](https://dataxapi.com/guides/tiktok-video-transcript/)