TikTok Transcript

Get native TikTok captions or an opted-in AI transcript by video URL, with timestamp segments when available. AI timing is approximate, not word-perfect.

CostAt least 10 credits / call

Try online

POST · https://api.nexscope.ai/social/tiktok/video/transcriptMCP · social_tiktok_video_transcript

What this API does

Get native TikTok captions or an opted-in AI transcript by video URL, with timestamp segments when available. AI timing is approximate, not word-perfect. The request accepts url, language, allow_long_transcription, use_ai_as_fallback. Its documented result includes platform, resourceStatus.

TikTok Transcript API use cases

Plan a TikTok Transcript request

A researcher checks the published operation description and supplies url, language, allow_long_transcription, use_ai_as_fallback for TikTok Transcript. The request stays within the supported parameters rather than assuming other platform capabilities.

Inspect TikTok Transcript results

An analyst reviews platform, resourceStatus from TikTok Transcript for the requested subject. Missing values remain explicit, and the response does not establish complete platform coverage.

Document TikTok Transcript observations

A researcher records the inputs and available results from TikTok Transcript alongside its published description. The record supports a scoped review without inferring unsupported actions, refresh intervals or broader conclusions.

TikTok Transcript API FAQ

What does the TikTok Transcript API return?

Get native TikTok captions or an opted-in AI transcript by video URL, with timestamp segments when available. AI timing is approximate, not word-perfect. The documented output includes platform, resourceStatus. It corresponds to the supplied url, language, allow_long_transcription, use_ai_as_fallback. Optional fields can be absent; a missing value should not be interpreted as a measured zero. Example values illustrate the response shape, rather than live account results.

How many credits does the TikTok Transcript API cost?

The current documented cost is At least 10 credits / call. This is the same cost shown at the top of this page. If a range or estimate is displayed, the final charge depends on the request. Review your available credits and the pricing page before calling the API, and check API usage records for the actual charge.

How do I call the TikTok Transcript API from my app or an MCP client?

Send a POST request to https://api.nexscope.ai/social/tiktok/video/transcript with your API key as a Bearer token and the JSON inputs shown in API integration. In a compatible MCP client such as Claude or Cursor, connect Nexscope and call social_tiktok_video_transcript. Use the MCP arguments shown in the MCP guide, or switch Online test to MCP to review its request before adding it to your app.

View plans and credits Connect this API with MCP

Try this API

Endpoint

https://api.nexscope.ai/social/tiktok/video/transcript

MCP method

social_tiktok_video_transcript

Step 1 of 3 · Authenticate

Authentication

All run endpoints require a user API key. Send it as a bearer token in the Authorization header.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx

Missing or invalid API keys return an authentication error. Manage keys from .

Step 2 of 3 · Send a request

POSThttps://api.nexscope.ai/social/tiktok/video/transcript

Run an API

Send a JSON request body using the parameters described below.

Example request

Replace YOUR_API_KEY, then run this command in your terminal.

curl -X POST 'https://api.nexscope.ai/social/tiktok/video/transcript' \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://www.tiktok.com/@stoolpresidente/video/7499229683859426602"
}'

Code example

{
  "url": "https://www.tiktok.com/@stoolpresidente/video/7499229683859426602"
}

Step 3 of 3 · Inspect the result

Check the response

Read code for the request status and data for the result. Open the parameter and response reference for the full field definitions.

HTTP status codes

Code	Description
200	Default HTTP response for both success and many business errors. Only outer JSON code 0 indicates success or asynchronous acceptance; inspect data for the result.
429	Execution admission rate limit; honor Retry-After when present.
503	Execution admission is temporarily unavailable; honor Retry-After when present.
Opt-in	X-Nexscope-Http-Status: semantic maps controller-handled business errors to HTTP status on run and task routes. Pre-authentication failures, such as a missing API key (code 11209), may still return HTTP 200 before this mapping. Always check the outer JSON code; malformed requests and infrastructure failures may also return non-200 HTTP responses.

View parameters & response Try online

All categories/ Social Data

POSThttps://api.nexscope.ai/social/tiktok/video/transcript

Run this API

Send a JSON request to execute this API and receive the documented response payload.

Open tester

Endpoint

Method	`POST`
Path	`https://api.nexscope.ai/social/tiktok/video/transcript`
Auth	`Bearer API key`
Content-Type	`application/json`

Request parameters

Name	Type	Required	Description
`url`	`string`	required	TikTok video URL Example: https://www.tiktok.com/@stoolpresidente/video/7499229683859426602
`language`	`string`	optional	Language of the transcript. 2 letter language code, ie 'en', 'es', 'fr', 'de', 'it', 'ja', 'ko', 'zh'
`allow_long_transcription`	`boolean`	optional	Paid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.
`use_ai_as_fallback`	`string`	optional	Set to 'true' to use paid AI only when existing captions are unavailable. Defaults to false. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.

Social data contract

Use your Nexscope API key. No supplier credentials are required. Requests reject unknown fields, including pageSize. URLs require HTTPS and an exact supported platform host and resource path. Documented YouTube video URLs may use youtu.be; other short links are unsupported. Check the request schema for supported fields and defaults.

Each request fetches one page. Continue manually with the returned nextCursor, or nextPage for Instagram Reels (pages 1–11). Cursors are opaque, unchanged strings up to 65536 UTF-8 bytes. No automatic pagination, retry, media download or transcription is performed. Repeated requests may purchase data again.

Resource status is independent of HTTP and billing: AVAILABLE, PARTIAL, PRIVATE, RESTRICTED, NOT_FOUND, NO_TRANSCRIPT or UNKNOWN can accompany code 0. Unknown values remain null; arrays remain empty arrays. fetchedAt is the response observation time; sourceFetchedAt is null without source evidence.

usage.billingStatus is NOT_CHARGED, SETTLED or UNKNOWN; chargedCredits is null when unconfirmed. Unknown charges never mean free. Completed lookups have a minimum charge of 10 credits, including cached, no-caption and unavailable-resource results; check API usage records for the actual charge. Parameter errors and unpublished APIs use the standard error envelope; upstream failures use code 13007, rate limits 429 and timeouts 408. Always check code and msg.

Response example

Platform response envelope. code 0 indicates success or acceptance; data contains the business result.

{
  "code": 0,
  "cost": "-1",
  "data": {
    "data": {
      "id": "7499229683859426602",
      "success": true,
      "transcript": "WEBVTT\n\n\n00:00:00.120 --> 00:00:01.840\nAlright, pizza review time.\n\n00:00:01.841 --> 00:00:03.761\nSal's Pizza Factory. Oh,\n\n00:00:03.762 --> 00:00:05.721\nit's Fucking Corn. We're in Charlotte.\n\n00:00:05.722 --> 00:00:07.861\nAlright man, any chance I can get a real quick picture?\n\n00:00:07.920 --> 00:00:10.040\nShaq or Dwight Howard? I gotta pick one.\\n",
      "transcript_with_timestamp": null,
      "url": "https://www.tiktok.com/@stoolpresidente/video/7499229683859426602"
    },
    "platform": "tiktok",
    "resourceStatus": "AVAILABLE",
    "usage": {
      "billingStatus": "UNKNOWN"
    }
  },
  "msg": null,
  "time": "2026-01-01 00:00:00",
  "traceId": null,
  "ts": "0"
}

Response fields

Name	Type	Required	Description
`code`	`integer`	required	0 means accepted or successful; nonzero is a platform error.
`cost`	`string`	required	Elapsed milliseconds, never credits; -1 outside web requests.
`data`	`any`	required	Data value used by this API operation.
`msg`	`string \| null`	required	Msg value used by this API operation.
`time`	`string`	required	Server local time: yyyy-MM-dd HH:mm:ss.
`traceId`	`string \| null`	required	Trace id value used by this API operation.
`ts`	`string`	required	Epoch milliseconds.

Any of option 1 — requires platform, resourceStatus, data, usage

Name	Type	Required	Description
`data`	`object`	required	Data value used by this API operation.
`data.data`	`object`	required	Data value used by this API operation.
`data.platform`	`string`	required	Platform value used by this API operation.
`data.resourceStatus`	`string`	required	Resource status value used by this API operation.
`data.usage`	`object`	required	Usage value used by this API operation.

Any of option 2

Name	Type	Required	Description
`data`	`null`	required	Data value used by this API operation.

Responses

Code	Description
200	Default HTTP response for both success and many business errors. Only outer JSON code 0 indicates success or asynchronous acceptance; inspect data for the result.
429	Execution admission rate limit; honor Retry-After when present.
503	Execution admission is temporarily unavailable; honor Retry-After when present.
Opt-in	X-Nexscope-Http-Status: semantic maps controller-handled business errors to HTTP status on run and task routes. Pre-authentication failures, such as a missing API key (code 11209), may still return HTTP 200 before this mapping. Always check the outer JSON code; malformed requests and infrastructure failures may also return non-200 HTTP responses.

Data source, freshness, and limitations

Source, freshness, coverage, rate limits, and estimation notes are not specified in this API definition unless they appear in the request or response field documentation above. Do not assume official marketplace data or real-time freshness when it is not explicitly documented.

Step 1 of 2 · Connect your MCP client

MCP

V2 recommended

Connect remote agents through the standard MCP 2025-11-25 Streamable HTTP endpoint. Use OAuth 2.1 Authorization Code with PKCE, or an API key for compatibility.

POST https://api.nexscope.ai/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/json

Authentication

OAuth clients request the mcp:tools scope. The endpoint's 401 response advertises protected-resource metadata for authorization discovery.

Step 2 of 2 · Call the tool

Call a tool

{
  "jsonrpc": "2.0",
  "id": "tool-call-1",
  "method": "tools/call",
  "params": {
    "name": "social_tiktok_video_transcript",
    "arguments": {
      "url": "https://www.tiktok.com/@stoolpresidente/video/7499229683859426602"
    }
  }
}

Legacy MCP v1

Existing API-key clients can continue using the compatibility endpoint. New integrations should use MCP v2.

GET / POST /mcp/legacy

What can you do with this API?

Data explained and practical use cases

AI Guide

Question

What data can TikTok Transcript provide, and how might I use it?

AI answer

Extracts existing transcripts, captions, or subtitles from a TikTok video by URL. Returns id, url, and transcript (native captions are WEBVTT-formatted; AI fallback returns text). Also includes top-level transcript_with_timestamp: an array of {start: number, end: number, text: string} sentence/phrase segments from native captions or AI, or null when speech or timing is unavailable. Times are seconds relative to the video. AI timings are approximate, not word-perfect. The existing transcript

Data category	Documented fields	How to use them
Request	`url`, `language`, `allow_long_transcription`, `use_ai_as_fallback`	Provide the required identifiers, filters, or paging inputs listed in the API document.
Response	`data.data`, `data.platform`, `data.resourceStatus`	Inspect returned values and source references; availability depends on the request and upstream source.

Review TikTok Transcript.
- Prompt example: “Retrieve TikTok Transcript for [public URL]. Summarize only the information actually returned and preserve source links when available. Report private, restricted, missing or partial results explicitly; missing values are not zero.”
Review Language-Specific Results.
- Prompt example: “Retrieve TikTok Transcript for [public URL] with [a supported language choice]. Follow the documented language option and report unavailable language-specific content. Do not fabricate a translation or claim that the option guarantees the language of every result.”
Transcribe Longer Content Within an Approved Budget.
- Prompt example: “Use TikTok Transcript for [public URL]. If the video exceeds the default transcription limit, explain the published duration limit and charging rule first. Enable the paid long-transcription option only after I approve the cost; stop if the duration is unsupported. If native captions are unavailable, enable the documented AI fallback only within that approved budget.”
Use AI Transcription Only When Captions Are Missing.
- Prompt example: “Use TikTok Transcript for [public URL]. Try the documented native-caption path first. Enable paid AI fallback only after I approve the charge and only when captions are unavailable. Distinguish generated transcription from native captions; leave paid long-transcription mode off unless separately approved.”

These are suggested workflows, not completed lookups. Report missing, restricted, or partial data explicitly; verify the live response before making a decision.

Online test

Execute the current API with your API key and JSON payload. Online tests use this site's configured API environment; the Endpoint and copyable examples use the public integration address.

One request fetches one page. Copy nextCursor into cursor, or nextPage into page (1–11 for Reels), then run manually. Repeated requests may purchase data again. Completed lookups have a minimum charge of 10 credits, including cached, no-caption, private, restricted and not-found results. Resource status and actual billing status are independent; null credits are unknown, never free. Check usage.billingStatus, usage.chargedCredits and API usage records for the actual charge.

Try it

Send a real request with the same contract shown in the reference.

Endpoint

/social/tiktok/video/transcript

MCP method

social_tiktok_video_transcript

API key*

JSON payload*

cURL

curl -X POST \
  https://api.nexscope.ai/social/tiktok/video/transcript \
  -H "Authorization: Bearer nk-..." \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://www.tiktok.com/@stoolpresidente/video/7499229683859426602" }'

Request estimate: Estimating…Usage based. The final charge depends on actual usage. Estimating does not run the API or charge credits.API usage records

Response

No response yet. Run the request to see the response here.

Related APIs

TikTok Collection Videos

Fetch videos saved in a public TikTok collection by its URL. Read video IDs, captions, authors and statistics, and continue with the returned cursor.

TikTok Trending Feed

Read TikTok's trending or For You feed for a selected region. Review returned video IDs, captions and engagement statistics for content discovery.

TikTok Live Info

Read curated TikTok live-room details using a room ID, including title, owner and viewer counts.

TikTok Profile

Look up a public TikTok profile by handle or user ID. Read identity, bio and account statistics, without fetching videos or follower lists.