POST
TikTok Video transcript full API
/v1/run/tiktok.video_transcript_full
Transcribe the spoken audio of a TikTok video with timed segments, speaker labels, and per-word confidence - for videos TikTok publishes no subtitle track for.
- Category SocialRequests / mo 1Routing 1 lane · no failover
Pricing
One price, in dollars
pay per request · no subscription · fallbacks added as the catalog growsRequest
Gateway request
discovered operation
Router
↓
↳ One lane serves this endpoint today, so a failed call has nowhere to fail over to. Failed attempts are never billed. Uptime, latency and traffic are measured through the gateway, last 30 days.
Try it
Make your first request
run it free, no key · same shape for every APISample response
Free runs return only the first 3 results. Fund a key to get the full response.
{
"data": {
"durationSeconds": 12.5,
"language": "en",
"segments": [
{
"endSeconds": 180,
"language": "en",
"speaker": "example",
"startSeconds": 180,
"text": "A short example description of this item.",
"words": [
{
"confidence": 1024,
"endSeconds": 180,
"speaker": "example",
"startSeconds": 180,
"word": "example"
}
]
}
],
"source": "https://example.com/page",
"transcript": "example"
},
"found": true
}Response interface
interface TiktokVideoTranscriptFullResponse {
data: {
durationSeconds?: number;
language?: string;
segments?: {
endSeconds: number;
language?: string;
speaker?: string;
startSeconds: number;
text: string;
words?: {
confidence: number;
endSeconds?: number;
speaker?: string;
startSeconds?: number;
word: string;
}[];
}[];
source: string;
transcript: string;
} | null;
found: boolean;
}Full parameter and response reference - every field, type, and example for this endpoint.
Reference
Request, response, and price
Last verified 2026-08-23 · uptime and latency measured over 30dPOST /v1/run/tiktok.video_transcript_full
curl -X POST https://api.getanyapi.com/v1/run/tiktok.video_transcript_full \
-H "Authorization: Bearer $ANYAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://www.tiktok.com/@thatdudecancook/video/7649086431641521421"}'| Field | Type | Example value |
|---|---|---|
| Request body | ||
| url | string | "https://www.tiktok.com/@thatdudecancook/video/7649086431641521421"TikTok video URL (e.g. "https://www.tiktok.com/@user/video/1234567890"). |
| Response | ||
| data | object | |
| data.durationSeconds | number | Video duration in seconds. |
| data.language | string | Detected spoken language of the audio (BCP-47 style code, e.g. "en"). |
| data.segments | object[] | Timed transcript segments in playback order, each with the recognizer's per-word confidence so low-confidence text can be treated as uncertain rather than quoted. Populated whenever the provider has data for the entity. |
| data.segments[].endSeconds | number | Segment end offset in seconds. |
| data.segments[].language | string | Detected language for this segment. |
| data.segments[].speaker | string | Recognizer speaker label for this segment (e.g. "SPEAKER_00"). Diarization is a guess, not an identification. |
| data.segments[].startSeconds | number | Segment start offset in seconds. |
| data.segments[].text | string | Text of this segment. |
| data.segments[].words | object[] | Per-word timing and recognizer confidence for this segment. |
| data.segments[].words[].confidence | number | Recognizer confidence for this word, 0 to 1. Low values mark words the recognizer guessed; they are common on names, jargon, and music. |
| data.segments[].words[].endSeconds | number | Word end offset in seconds. |
| data.segments[].words[].speaker | string | Recognizer speaker label for this word. |
| data.segments[].words[].startSeconds | number | Word start offset in seconds. |
| data.segments[].words[].word | string | The recognized word. |
| data.source | string | How the text was produced. Always "audio_asr" on this endpoint: the words come from automatic speech recognition over the audio, not from a caption track the platform published. Populated whenever the provider has data for the entity. |
| data.transcript | string | Full spoken-word transcript, machine-transcribed from the video's audio track. Populated whenever the provider has data for the entity. |
| found | boolean | |
| Price | ||
| Price per request | USD | $0.0176 |
| Price /1k req | USD | $17.60 |
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 timed segments, speaker labels, and per-word confidence - for videos TikTok publishes no subtitle track for. AnyAPI returns one normalized schema whichever source serves it. It costs from $17.60 per 1,000 requests, in US dollars with no subscription and no monthly minimum. Over the last 30 days, 100.0% of TikTok video transcript full calls through AnyAPI succeeded, with a median response time of 17.4 seconds across 1 measured calls.
It costs from $17.60 per 1,000 requests, in US dollars with no subscription and no monthly minimum. You fund one USD wallet, each call draws it down, and a failed request costs $0.
Transcribe the spoken audio of a TikTok video with timed segments, speaker labels, and per-word confidence - for videos TikTok publishes no subtitle track for. 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, 100.0% of TikTok video transcript full calls through AnyAPI succeeded, with a median response time of 17.4 seconds across 1 measured calls. These are AnyAPI's own measurements of traffic through the gateway, recomputed continuously, not a published service-level target.
More to call
Other TikTok endpoints
Profile · from $0.90 /1k reqProfile videos · from $1.20 /1k reqVideo transcript · from $2.00 /1k reqKeyword search · from $1.20 /1k reqVideo · from $0.90 /1k reqVideo comments · from $1.44 /1k reqUser search · from $1.20 /1k reqAd library ad · from $1.20 /1k reqAd library search · from $2.00 /1k reqAd transparency search · from $0.90 /1k reqAudience demographics · from $18.00 /1k reqComment replies · from $2.00 /1k reqFollowers · from $2.00 /1k reqFollowing · from $2.00 /1k reqHashtag videos · from $1.44 /1k reqLive · from $2.00 /1k reqProfile region · from $2.00 /1k reqSearch hashtag · from $2.00 /1k reqSearch top · from $2.00 /1k reqSong · from $2.00 /1k reqSong videos · from $2.00 /1k reqTop ads search · from $1.20 /1k reqTrending feed · from $2.00 /1k reqTrending hashtags · from $1.20 /1k req
Get started
Two ways to start on AnyAPI
Humans fund a USD wallet and pay per request. Agents point a coding agent at one URL and onboard themselves.
Works with
Terminal agentsClaude CodeCursorCodexMCP clients