Discover/TokScript API
live

TokScript APItokscript.com

Fetch timestamped speech-to-text transcripts for TikTok videos plus video metadata, author details, and engagement stats via a single API endpoint.

Endpoint health
verified 3d ago
get_transcript
1/1 passing latest checkself-healing
Endpoints
1
Updated
26d ago

What is the TokScript API?

The TokScript API exposes 1 endpoint — get_transcript — that returns a complete speech-to-text transcript for any public TikTok video across 14 distinct response fields. The response includes timestamped text segments, the full combined transcript text, detected language, video metadata such as dimensions and creation time, author profile data including follower count and verification status, engagement statistics, and associated music details.

Try it
Full TikTok video URL (e.g. https://www.tiktok.com/@username/video/<video_id>)
api.parse.bot/scraper/b2d5c607-3d34-454f-8e71-f6d43c9f4ffb/<endpoint>
Ready to send
Fill in the parameters and hit sign in to send to see live response data here.
Call it over HTTPgrab a free API key at signup
curl -X GET 'https://api.parse.bot/scraper/b2d5c607-3d34-454f-8e71-f6d43c9f4ffb/get_transcript?video_url=https%3A%2F%2Fwww.tiktok.com%2F%40brookemonk_%2Fvideo%2F7603118297403378975' \
  -H 'X-API-Key: $PARSE_API_KEY'
Python SDK · recommended

Typed, relational, agent-ready

A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.

  • Fully typed · autocompletes
  • Objects link to objects
  • Typed errors & pagination

Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:

uv add parse-sdk
uv run parse init
uv run parse add --marketplace tokscript-com-api

uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.

"""TokScript SDK — fetch TikTok video transcripts with metadata."""
from parse_apis.tokscript_tiktok_transcript_api import TokScript, VideoNotFound

client = TokScript()

# Fetch transcript for a TikTok video
try:
    result = client.transcripts.get(video_url="https://www.tiktok.com/@brookemonk_/video/7603118297403378975")
    print(result.video.id, result.video.duration)
    print(result.author.nickname, result.author.verified, result.author.follower_count)
    print(result.stats.play_count, result.stats.like_count)
    print(result.music.title, result.music.author)
    print(result.transcript.method, result.transcript.language)
    print(f"Segments: {len(result.transcript.segments)}")
    if result.transcript.segments:
        seg = result.transcript.segments[0]
        print(f"First segment: [{seg.start} -> {seg.end}] {seg.text}")
    print(f"Full text preview: {result.transcript.full_text[:100]}")
except VideoNotFound as exc:
    print(f"Video not found: {exc}")

print("exercised: transcripts.get / Video / Author / Stats / Music / TranscriptContent / Segment")
All endpoints · 1 totalmissing one? ·

Get the transcript (speech-to-text) for a TikTok video. Returns timestamped text segments, full combined text, video metadata, author details, and engagement statistics. Videos without speech or deleted videos will return an upstream_error.

Input
ParamTypeDescription
video_urlrequiredstringFull TikTok video URL (e.g. https://www.tiktok.com/@username/video/<video_id>)
Response
{
  "type": "object",
  "fields": {
    "music": "object containing title, author, duration",
    "stats": "object containing play_count, like_count, comment_count, share_count, collect_count",
    "video": "object containing id, description, create_time, duration, width, height, cover, location_created",
    "author": "object containing id, unique_id, nickname, avatar, verified, follower_count",
    "transcript": "object containing full_text, segments (array of timestamped text), method, language"
  },
  "sample": {
    "data": {
      "music": {
        "title": "Piano famous song Chopin Deep deep clear beauty",
        "author": "RYOpianoforte",
        "duration": 342
      },
      "stats": {
        "like_count": 8600000,
        "play_count": 273600000,
        "share_count": 135800,
        "collect_count": "445193",
        "comment_count": 55800
      },
      "video": {
        "id": "7603118297403378975",
        "cover": "https://p16-common-sign.tiktokcdn-us.com/tos-useast8-p-0068-tx2/oEx0wEBNIiAimy7EfCAAIxqiUdDg5Tpm92SIqs~tplv-tiktokx-origin.image",
        "width": 720,
        "height": 1280,
        "duration": 62,
        "create_time": "1770238937",
        "description": "",
        "location_created": "US"
      },
      "author": {
        "id": "6732675975610074118",
        "avatar": "https://p16-common-sign.tiktokcdn-us.com/tos-maliva-avt-0068/81dd03ab48e571529193c93e79d59201~tplv-tiktokx-cropcenter:100:100.jpeg",
        "nickname": "Brooke Monk",
        "verified": true,
        "unique_id": "brookemonk_",
        "follower_count": 46500000
      },
      "transcript": {
        "method": "native-tiktok",
        "language": "eng-US",
        "segments": [
          {
            "end": "00:00:01",
            "text": "Now.",
            "start": "00:00:01"
          },
          {
            "end": "00:00:04",
            "text": "Yes. Yes, yes. Okay.",
            "start": "00:00:02"
          }
        ],
        "full_text": "Now. Yes. Yes, yes. Okay."
      }
    },
    "status": "success"
  }
}

About the TokScript API

What the API Returns

The get_transcript endpoint accepts a single required parameter, video_url, which must be the full TikTok URL in the format https://www.tiktok.com/@username/video/<video_id>. The response is organized into four top-level objects: transcript, video, author, and stats, plus a music object.

Transcript Object

The transcript object contains full_text (the entire spoken content as a single string), segments (an array of timestamped text chunks useful for syncing captions or searching by time offset), method (the transcription method used), and language (the detected language of the speech). If the video contains no speech or has been deleted, the endpoint returns an upstream_error rather than an empty transcript.

Video, Author, and Engagement Data

The video object includes id, description, create_time, duration, width, height, cover (thumbnail URL), and location_created. The author object provides id, unique_id, nickname, avatar, verified flag, and follower_count. The stats object exposes play_count, like_count, comment_count, share_count, and collect_count. The music object returns title, author, and duration for the audio track used in the video.

Reliability & maintenanceVerified

The TokScript API is a managed, monitored endpoint for tokscript.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when tokscript.com changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.

This isn't an official tokscript.com API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.

Last verified
3d ago
Latest check
1/1 endpoint passing
Maintenance
Monitored & self-healing
Will this API break when the source site changes?+
It's built not to. Every endpoint is health-checked on a schedule with automated test probes. When the source site changes and a check fails, the API is automatically queued for repair and re-verified — that's the self-healing layer. Each API page shows when its endpoints were last verified. And because marketplace APIs are shared, any fix reaches everyone using it.
Is this an official API from the source site?+
No — Parse APIs are independent, managed REST wrappers over publicly available data. That is the point: where a site has no official API (or only a limited one), Parse gives you a maintained, monitored endpoint for that data and keeps it working as the site changes — so you get a stable contract over a source that never promised one.
Can I fix or extend this API myself if I need a new endpoint or field?+
Yes — and you don't have to wait on us. This API was generated by the Parse agent, which stays attached. Describe the change in plain English ("add an endpoint that returns reviews", "fix the price field") in the revise box on the API page or via the revise_api MCP tool, and the agent rebuilds it against the live site in minutes. Contributing the change back to the public API is free.
What happens if I call an endpoint that has an issue?+
Errors are machine-readable: a bad call returns a clean status with the list of available endpoints and a repair hint, so an agent (or you) can recover or trigger a fix instead of failing silently. Confirmed failures feed the automatic repair queue.
Common use cases
  • Index TikTok video content by spoken keywords using full_text from the transcript object for searchable archives.
  • Build caption overlays or subtitle files using the segments array with precise timestamps from get_transcript.
  • Filter or rank videos by engagement using play_count, like_count, and share_count from the stats object.
  • Identify verified creators and cross-reference follower counts using verified and follower_count from the author object.
  • Track TikTok content by geographic origin using location_created from the video object.
  • Detect language distribution across a set of videos using the language field in the transcript object.
  • Correlate background music tracks with transcript content using the music object's title and author fields.
Pricing & limitsSee full pricing →
TierPriceCredits/monthRate limit
Free$0/mo1005 req/min
Hobby$30/mo1,00020 req/min
Developer$100/mo5,000100 req/min

One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.

Frequently asked questions
Does TikTok have an official developer API that covers transcripts?+
TikTok provides a Research API (developers.tiktok.com/products/research-api) for academic and research use, but it does not expose speech-to-text transcripts. The TokScript API covers transcript data, video metadata, author details, and engagement stats that the official Research API does not provide.
What does get_transcript return for a video with no spoken audio?+
If a TikTok video contains no speech — such as a music-only or silent video — or if the video has been deleted, the endpoint returns an upstream_error response rather than an empty transcript object. The music and stats fields are not guaranteed to populate in this case.
Does the API cover TikTok comments or replies?+
Not currently. The API covers transcript content, video metadata, author profile data, and engagement counts. It does not return comments, replies, or comment threads. You can fork this API on Parse and revise it to add a comments endpoint if that data is needed.
Can I retrieve transcripts for multiple videos in a single call?+
The get_transcript endpoint accepts one video_url per request. Batch lookups across multiple videos are not supported in a single call. You can fork the API on Parse and revise it to add a batch endpoint that accepts multiple URLs.
How fresh is the engagement data returned with each transcript?+
Engagement stats — play_count, like_count, comment_count, share_count, and collect_count — reflect the state of the video at the time the request is made. The API does not return historical snapshots or time-series data for these metrics.
Page content last updated . Spec covers 1 endpoint from tokscript.com.
Related APIs in Social MediaSee all →
tiktok.com API
Retrieve detailed information about any public TikTok video including captions, media URLs, view counts, likes, and shares, plus access all comments posted on that video. Perfect for analyzing trending content, monitoring video performance, or building applications that need TikTok video data.
library.tiktok.com API
Search TikTok's Commercial Content Library to discover ads by company name or keyword, then view detailed information like creative format, scheduling dates, audience targeting, and video thumbnails. Monitor competitor advertising strategies and track ad campaigns across supported regions.
toutiao.com API
Browse personalized news feeds, discover trending articles and hot topics, search content across categories, view detailed articles with comments, and explore author profiles on Toutiao. Access video feeds and stay updated with the latest news and trending stories all in one place.
fishtank.live API
Access clips, episodes, contestant information, and live stream updates from Fishtank.live to browse content, check leaderboard rankings, and track live broadcast status. Get detailed information about specific clips and episodes, or discover random clips and current stox data.
twitch.tv API
Search for Twitch streamers and channels, view their profiles and streaming details, and discover live streams organized by category. Find the content and creators you want to watch all in one place.
stocktwits.com API
Discover which stocks are generating the most buzz on Stocktwits by accessing real-time trending symbols along with company names, trending scores, current price data, and community sentiment summaries. Stay ahead of market conversations by monitoring what the investing community is actively discussing and trading.
insights.trendforce.com API
Access semiconductor and AI industry analysis articles from TrendForce Insights, browsing post listings and retrieving full article content organized into text sections and figures. Perfect for staying updated on tech industry trends and feeding structured article data into language models for analysis.
threads.com API
Search for posts and users on Threads by keyword to discover content, view engagement metrics like likes and replies, and explore user profiles with their media. Find trending discussions and connect with creators all in one search experience.