TikTok API

TikTok Video transcript full API

Transcribe the spoken audio of a TikTok video with AnyAPI's own speech-to-text: timed sentence-level segments, speaker labels, detected language, and optional per-word timings, for videos TikTok publishes no caption track for and for videos whose caption track gets the words wrong. AnyAPI downloads the video and runs the audio through MAI-Transcribe-2 rather than reading anything TikTok wrote, which is why it handles non-English speech and hears words the native captions mishear. The answer also carries the video's id, URL, creator handle, and cover image. Turn on hostVideo to also get the MP4 on a hosted link that plays without TikTok's signed, short-lived CDN URL expiring on you. If you only want whatever TikTok itself published and you want it for a tenth of the price, tiktok.video_transcript is that.

$5.94/1k audio minutes, pay per request, no subscription.

@theodorekitchen on TikTok
tiktok.com/@theodorekitchen/video/7458219903341129744

@theodorekitchen

Follow
Video transcript
0:00

Okay so this is the three ingredient dinner that saved my week.

What the API returnedsegments[0]
{
"text": "Okay so this is the three ingredient dinner that saved my week.",
"startSeconds": 0,
"endSeconds": 3.8,
"language": "en",
"speaker": "speaker_1",
"words": object[]
}
Uptime
98.67%
30d · 6,790 calls
Requests
6,838
30d · weekly, last 12 wks
Response
7.0s
median · 30d

Try it

Get TikTok video transcript full in one request

Open in
Get a free key
Sample response
Free runs return only the first 3 results. Fund a key to get the full response.

This sample shows 16 of 24 fields. See every field

{
  "found": true,
  "data": {
    "id": "7458219903341129744",
    "url": "https://www.tiktok.com/@theodorekitchen/video/7458219903341129744",
    "ownerUsername": "theodorekitchen",
    "thumbnailUrl": "https://p16-sign-va.tiktokcdn.com/obj/tos-useast5-p-0068-tx/theodorekitchen-cover-7458219903341129744~tplv-obj.jpeg?x-signature=Xa4bDe6f",
    "transcript": "Okay so this is the three ingredient dinner that saved my week. You just need butter, garlic, and a rotisserie chicken. Shred it up, melt the butter with the garlic until it smells amazing, toss it all together, and that is it. Fifteen minutes, done.",
    "language": "en",
    "source": "audio_asr",
    "durationSeconds": 41.9,
    "segments": [
      {
        "text": "Okay so this is the three ingredient dinner that saved my week.",
        "startSeconds": 0,
        "endSeconds": 3.8,
        "language": "en",
        "speaker": "speaker_1"
      },
      {
        "text": "You just need butter, garlic, and a rotisserie chicken.",
        "startSeconds": 3.9,
        "endSeconds": 7.2,
        "language": "en",
        "speaker": "speaker_1"
      },
      {
        "text": "Shred it up, melt the butter with the garlic until it smells amazing, toss it all together, and that is it.",
        "startSeconds": 7.3,
        "endSeconds": 13.6,
        "language": "en",
        "speaker": "speaker_1"
      },
      {
        "text": "Fifteen minutes, done.",
        "startSeconds": 13.7,
        "endSeconds": 15.1,
        "language": "en",
        "speaker": "speaker_1"
      }
    ]
  }
}

Full parameter and response reference - every field, type, and example for this endpoint.

Reference

One request, one response shape.

Every field you send and every field you get back, each with a real example.

Last verified 2026-11-22 · uptime and latency measured over 30d

Request body

JSON, posted to this endpoint.

  • urlstring

    https://www.tiktok.com/@theodorekitchen/video/7458219903341129744

    TikTok video URL (e.g. "https://www.tiktok.com/@user/video/1234567890").

  • hostVideoboolean

    Also store the video and return a hosted MP4 link that plays without TikTok's signed CDN URL. Charged as an extra on top of the transcript.

  • wordTimestampsboolean

    Return per-word timings inside each segment. Words carry timings only; the recognizer scores a phrase rather than a word, so there is no per-word confidence to report.

You send. A small JSON body. The values shown are examples to replace with your own.

Response

JSON, one example value per field.

datadata
  • bytesinteger

    Size of the hosted MP4 in bytes.

  • durationSecondsnumber

    41.9

    Video duration in seconds.

  • expiresUtcnumber

    When the hosted link stops working. UTC epoch timestamp in seconds (Unix time). Multiply by 1000 for a JS Date in milliseconds.

  • hostedUrlstring

    Hosted MP4 link, returned only when the request set hostVideo. It plays without TikTok's signed CDN URL and without any cookie, and it stops working at expiresUtc.

  • idstring

    7458219903341129744

    TikTok video id.

  • languagestring

    en

    Detected spoken language of the audio (BCP-47 style code, e.g. "en").

  • ownerUsernamestring

    theodorekitchen

    Creator handle, without the leading @.

  • source"audio_asr" | "no_audio" | "transcript_unavailable"

    audio_asr

    How the text was produced. "audio_asr" means the words come from speech recognition over the video's audio, never from a caption track TikTok published - for TikTok's own captions, use tiktok.video_transcript. "transcript_unavailable" means recognition did not complete for this video, so the transcript is empty for that reason rather than because the video has no speech in it; the rest of the record is still what we resolved, and no audio time is charged. "no_audio" means there was nothing to listen to: the video has no audio track, or the post has no video. The transcript is empty because that is the answer, the rest of the record is still what we resolved, and only the request price is charged, with no audio time. Populated whenever the provider has data for the entity.

  • thumbnailUrlstring

    https://p16-sign-va.tiktokcdn.com/obj/tos-useast5-p-0068-tx/theodorekitchen-cover-7458219903341129744~tplv-obj.jpeg?x-signature=Xa4bDe6f

    Cover image for the video. A signed, short-lived TikTok CDN URL, often served as HEIC rather than JPEG, so fetch it promptly and transcode if you need broad browser support.

  • transcriptstring

    Okay so this is the three ingredient dinner that saved my week. You just need butter, garlic, and a rotisserie chicken. Shred it up, melt the butter with the garlic until it smells amazing, toss it all together, and that is it. Fifteen minutes, done.

    Full spoken-word transcript, recognized from the video's audio track. Populated whenever the provider has data for the entity.

  • urlstring

    https://www.tiktok.com/@theodorekitchen/video/7458219903341129744

    Canonical URL of the video this transcript came from.

each segmentdata.segments[]

Timed transcript segments in playback order, one per sentence, so a segment locates a specific line in the video rather than a whole speaker turn. Populated whenever the provider has data for the entity.

  • endSecondsnumber

    3.8

    Segment end offset in seconds, taken from the last word it contains.

  • languagestring

    en

    Detected language for this segment.

  • speakerstring

    speaker_1

    Speaker label for this segment, stable within one response and meaningless across responses. Telling voices apart is a guess, not an identification, and the label is not a name.

  • startSecondsnumber

    0

    Segment start offset in seconds, taken from the first word it contains.

  • textstring

    Okay so this is the three ingredient dinner that saved my week.

    Text of this segment.

each worddata.segments[].words[]

Per-word timings for this segment, returned only when the request set wordTimestamps. Words carry no confidence score: the recognizer scores a phrase rather than a word.

  • endSecondsnumber

    Word end offset in seconds.

  • startSecondsnumber

    Word start offset in seconds.

  • textstring

    The recognized word, in display form with its own punctuation.

top level
  • foundboolean

    true

  • reason"not_found"

    Present only when `found` is false, and says why there is no result. `not_found`: the source states the target does not exist, or returned nothing for it. A `found: false` answer is a successful call, not an error, and `costUsd` is what it actually cost.

You get back. Named, typed fields in the same shape whichever source answers.

FAQ

About the TikTok Video transcript full API

The AnyAPI TikTok Video transcript full API returns TikTok video transcript full data as normalized JSON from one POST call to /v1/run/tiktok.video_transcript_full. Transcribe the spoken audio of a TikTok video with AnyAPI's own speech-to-text: timed sentence-level segments, speaker labels, detected language, and optional per-word timings, for videos TikTok publishes no caption track for and for videos whose caption track gets the words wrong. AnyAPI downloads the video and runs the audio through MAI-Transcribe-2 rather than reading anything TikTok wrote, which is why it handles non-English speech and hears words the native captions mishear. The answer also carries the video's id, URL, creator handle, and cover image. Turn on hostVideo to also get the MP4 on a hosted link that plays without TikTok's signed, short-lived CDN URL expiring on you. If you only want whatever TikTok itself published and you want it for a tenth of the price, tiktok.video_transcript is that. AnyAPI returns one normalized schema whichever source serves it. It costs $5.94 per 1,000 audio minutes, and never more than $0.095 for a single request, in US dollars with no subscription and no monthly minimum. Over the last 30 days, 98.7% of TikTok video transcript full calls through AnyAPI succeeded, with a median response time of 7.0 seconds across 6,790 measured calls.

It costs $5.94 per 1,000 audio minutes, and never more than $0.095 for a single request, in US dollars with no subscription and no monthly minimum. You fund one USD wallet and each call draws it down. Some failed wallet-funded requests incur processing charges that we pass through at cost, with no markup; the error response shows the amount charged.

Transcribe the spoken audio of a TikTok video with AnyAPI's own speech-to-text: timed sentence-level segments, speaker labels, detected language, and optional per-word timings, for videos TikTok publishes no caption track for and for videos whose caption track gets the words wrong. AnyAPI downloads the video and runs the audio through MAI-Transcribe-2 rather than reading anything TikTok wrote, which is why it handles non-English speech and hears words the native captions mishear. The answer also carries the video's id, URL, creator handle, and cover image. Turn on hostVideo to also get the MP4 on a hosted link that plays without TikTok's signed, short-lived CDN URL expiring on you. If you only want whatever TikTok itself published and you want it for a tenth of the price, tiktok.video_transcript is that. The response is normalized JSON with the same envelope every AnyAPI endpoint returns, so parsing a second endpoint is a change of URL and nothing else.

Over the last 30 days, 98.7% of TikTok video transcript full calls through AnyAPI succeeded, with a median response time of 7.0 seconds across 6,790 measured calls. These are AnyAPI's own measurements of traffic through the gateway, recomputed continuously, not a published service-level target.

Yes. A new AnyAPI account starts with $0.10 of free balance and no card required, which covers at least 1 TikTok Video transcript full calls at up to $0.095 each.

Send a POST request to https://api.getanyapi.com/v1/run/tiktok.video_transcript_full with your AnyAPI key in an "Authorization: Bearer" header and the input as a JSON body. The same key and the same wallet work on every AnyAPI endpoint.

No. You add US dollars to one prepaid AnyAPI balance and each request draws it down. There is no monthly plan and no minimum, and the same balance pays for every AnyAPI endpoint.

Yes. Install @getanyapi/sdk from npm for TypeScript or getanyapi from pip for Python. Both call every AnyAPI endpoint with the same key, and any HTTP client works too.

Yes. An agent can connect to the AnyAPI MCP server at https://api.getanyapi.com/mcp, or create its own free-trial key with one unauthenticated POST to https://api.getanyapi.com/agent/signup and call this endpoint over HTTP.