TikTok Video Transcript (Speech to Text)
Speech-to-text transcript of a public TikTok video with timed segments and optional word timings, billed per started audio minute.
- Price per call
- 3 credits
- per successful call
- Price ceiling
- 33 credits
- if a call is retried elsewhere
- Failed calls
- Free
- retried automatically
- Billed
- Per call
- only on success
Endpoint
api.primaryapi.com/ v1/ run/ tiktok. video_transcript_fullAuth: API key with run or full access, or a dashboard session
Send the input below as a JSON body. The call is routed to a healthy upstream; if an attempt fails, it is retried automatically inside the same request and you pay only for the answer you get. To check an input and see the exact price without running anything, call POST /v1/quote/tiktok.video_transcript_full with the same body (free).
Example request
curl -sS -X POST "https://api.primaryapi.com/v1/run/tiktok.video_transcript_full" \
-H "Authorization: Bearer $PRIMARYAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://www.tiktok.com/@scout2015/video/6718335390845095173"}'const res = await fetch('https://api.primaryapi.com/v1/run/tiktok.video_transcript_full', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.PRIMARYAPI_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
url: 'https://www.tiktok.com/@scout2015/video/6718335390845095173',
}),
});
const body = await res.json();
if (!res.ok) throw new Error(`${body.code}: ${body.error}`);
// found:false is a successful answer ("does not exist"), not an error
console.log(body.output.found ? body.output.data : body.output.reason, body.credits);import os
import requests
res = requests.post(
"https://api.primaryapi.com/v1/run/tiktok.video_transcript_full",
headers={"Authorization": f"Bearer {os.environ['PRIMARYAPI_API_KEY']}"},
json={
"url": "https://www.tiktok.com/@scout2015/video/6718335390845095173",
},
timeout=60,
)
body = res.json()
if not res.ok:
raise RuntimeError(f"{body['code']}: {body['error']}")
# found=False is a successful answer ("does not exist"), not an error
print(body["output"]["data"] if body["output"]["found"] else body["output"]["reason"], body["credits"]){
"name": "run_api",
"arguments": {
"sku": "tiktok.video_transcript_full",
"input": {
"url": "https://www.tiktok.com/@scout2015/video/6718335390845095173"
}
}
}Price this exact input first (free)
curl -sS -X POST "https://api.primaryapi.com/v1/quote/tiktok.video_transcript_full" \
-H "Authorization: Bearer $PRIMARYAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://www.tiktok.com/@scout2015/video/6718335390845095173"}'Returns credits (what the call is expected to cost) and maxCredits (the most it can cost, which is set aside while it runs). Invalid input fails here the same way it would on run.
Input
JSON body fields. Unknown fields are rejected with 400 invalid_input (never silently ignored). You may add the routing controls preferLatencyUnderMs and maxCredits to the same object.
urlstringrequired- TikTok post URL on tiktok.com: a video or photo post (https://www.tiktok.com/@<user>/video/<id> or /photo/<id>) or a vm.tiktok.com / vt.tiktok.com share link.max 2048 chars · format: uri
wordTimestampsbooleandefaultfalse- Also return per-word timings.
hostVideobooleandefaultfalse- AnyAPI-compatible flag. Media hosting is not offered: the call still succeeds and hostedUrl is null.
limitintegerdefault10- Maximum audio minutes you agree to pay for (1-60, default 10). The price is charged per started minute, capped here.1–60
Output
When output.found is true, output.data has these fields.
idstring | null- TikTok video id
urlstring- Video URL
ownerUsernamestring | null- Creator @handle when the source provides it
thumbnailUrlstring | null- Cover image URL (signed, expires)
languagestring | null- Detected spoken language (ISO 639-1 or name, as the recognizer reports it)
durationSecondsnumber | null- Audio length in seconds
transcriptstring- Full transcript text (empty for silent videos)
segmentsobject[]segments[].startSecondsnumber | null- Segment start, seconds from the beginning of the video
segments[].endSecondsnumber | null- Segment end, seconds from the beginning of the video
segments[].textstringsegments[].speakerstring | null- Always null: Whisper does no diarization
wordsobject[] | null- Per-word timings when wordTimestamps=true
words[].startSecondsnumber | nullwords[].endSecondsnumber | nullwords[].textstringsourceenum- asr = our speech-to-text; captions = TikTok caption track; captions_or_asr = the source does not say whichone of: asr, captions, captions_or_asr
hostedUrlstring | null- Always null: media hosting is not offered (AnyAPI hostVideo parity field)
bytesinteger | null- Always null (hosting not offered)
expiresUtcstring | null- Always null (hosting not offered)
TypeScript type
/** output.data when output.found is true */
type TiktokVideoTranscriptFull = {
/** TikTok video id */
id: string | null;
/** Video URL */
url: string;
/** Creator @handle when the source provides it */
ownerUsername: string | null;
/** Cover image URL (signed, expires) */
thumbnailUrl: string | null;
/** Detected spoken language (ISO 639-1 or name, as the recognizer reports it) */
language: string | null;
/** Audio length in seconds */
durationSeconds: number | null;
/** Full transcript text (empty for silent videos) */
transcript: string;
segments: {
/** Segment start, seconds from the beginning of the video */
startSeconds: number | null;
/** Segment end, seconds from the beginning of the video */
endSeconds: number | null;
text: string;
/** Always null: Whisper does no diarization */
speaker: string | null;
}[];
/** Per-word timings when wordTimestamps=true */
words: {
startSeconds: number | null;
endSeconds: number | null;
text: string;
}[] | null;
/** asr = our speech-to-text; captions = TikTok caption track; captions_or_asr = the source does not say which */
source: "asr" | "captions" | "captions_or_asr";
/** Always null: media hosting is not offered (AnyAPI hostVideo parity field) */
hostedUrl: string | null;
/** Always null (hosting not offered) */
bytes: number | null;
/** Always null (hosting not offered) */
expiresUtc: string | null;
};If what you asked about does not exist, is private, or a search matches nothing, the call still succeeds: output.found is false, output.data is null and output.reason says why. Such misses are free unless the notes below say misses are billed, in which case a miss costs the price of one call.
Example response
Values are placeholders that follow the output schema (strings as "string", numbers as 0); credits shows what this call would cost at the usual price.
{
"output": {
"found": true,
"data": {
"id": "6718335390845095173",
"url": "https://www.tiktok.com/@scout2015/video/6718335390845095173",
"ownerUsername": "scout2015",
"thumbnailUrl": null,
"language": "English",
"durationSeconds": 10,
"transcript": "Scramble up your name and I will try to guess it.",
"segments": [
{
"startSeconds": 0,
"endSeconds": 3.4,
"text": "Scramble up your name",
"speaker": null
},
{
"startSeconds": 3.4,
"endSeconds": 6.1,
"text": "and I will try to guess it.",
"speaker": null
}
],
"words": null,
"source": "asr",
"hostedUrl": null,
"bytes": null,
"expiresUtc": null
}
},
"provider": "PrimaryAPI",
"credits": 3,
"items": 1,
"requestId": "req_01JBXK6Y2N9V8T4R3Q2P1M0A7Z"
}Pricing and reliability
Calls go only to upstreams that are healthy right now. If an attempt fails, the call is retried automatically inside the same request; a failed attempt costs nothing, and a call never costs more than its quote’s maxCredits. Live figures below are measured on real traffic.
Success rate, uptime, latency and call counts are measured live from real traffic over 30 days and show “—” until there is data.
Errors
Errors are JSON { code, error, requestId } and are never charged. The ones to handle for this endpoint:
- invalid_inputThe request failed validation before anything ran.
- unauthorizedNo valid API key or session was presented.
- insufficient_balanceThe balance cannot cover the most this call could cost.
- key_limit_reachedThe key’s own spend limit is used up for the current window.
- trial_cap_reachedAn agent trial key has used its whole trial budget.
- forbiddenThe credential is valid but may not do this.
- not_foundThe thing addressed by the URL does not exist for you.
- idempotency_conflictThe
Idempotency-Keyis already bound to a different request. - rate_limitedToo many requests in the current window.
- all_sources_failedThe call could not be answered, even after automatic retries.
- service_unavailableThis API cannot run in this deployment right now.
- timeoutThe request passed its deadline before it finished.
Notes
Billed per started minute (min 1, max `limit`). Third-party creator audio: transcripts are derivative processing, no media is stored.
More TikTok endpoints
- TikTok Ad Library Ad2 credits
- TikTok Ad Library Search3 credits
- TikTok Ad Transparency Search3 credits
- TikTok Audience Demographics62 credits
- TikTok Comment Replies2 credits
- TikTok Followers2 credits
- TikTok Following2 credits
- TikTok Hashtag Search3 credits
- TikTok Hashtag Videos3 credits
- TikTok Keyword Search2 credits
- TikTok Live2 credits
- TikTok Photos2 credits
- TikTok Playlist Videos2 credits
- TikTok Profile2 credits
- TikTok Profile Contact Info3 credits
- TikTok Profile Region2 credits
- TikTok Profile Reposts2 credits
- TikTok Profile Videos2 credits
- TikTok Search Suggestions2 credits
- TikTok Song2 credits
- TikTok Song Videos2 credits
- TikTok Top Ads Search2 credits
- TikTok Top Search2 credits
- TikTok Trending Feed3 credits
- TikTok Trending Hashtags2 credits
- TikTok User Search2 credits
- TikTok Video1 credit
- TikTok Video Comments2 credits
- TikTok Video Download1 credit
- TikTok Video Transcript2 credits
- TikTok Photo SearchPlanned
- TikTok Profile PlaylistsPlanned
- TikTok User StoriesPlanned
Generated from the PrimaryAPI catalog. Machine-readable contract: GET https://api.primaryapi.com/v1/apis/tiktok.video_transcript_full.