# TikTok Video Transcript (Speech to Text) (`tiktok.video_transcript_full`)

Speech-to-text transcript of a public TikTok video with timed segments and optional word timings, billed per started audio minute.

Docs: https://primaryapi.com/docs/api-reference/tiktok/video_transcript_full

- Endpoint: `POST https://api.primaryapi.com/v1/run/tiktok.video_transcript_full`
- Category: Social · Platform: `tiktok` · Kind: transcript · Status: live
- Price: 3 credits per call; up to 33 credits if a call is retried elsewhere. A quote’s `maxCredits` is the most a given call can cost.
- Billing unit: per successful call
- Reliability: routed to a healthy upstream and retried automatically when an attempt fails; live 30-day status: `GET https://api.primaryapi.com/v1/status/apis?sku=tiktok.video_transcript_full`
- Execution: synchronous (answers 202 only if it outlives the wait window)

## Input

| Field | Type | Required | Default | Constraints | Description |
|---|---|---|---|---|---|
| `url` | string | yes |  | max 2048 chars; format: uri | 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. |
| `wordTimestamps` | boolean | no | false |  | Also return per-word timings. |
| `hostVideo` | boolean | no | false |  | AnyAPI-compatible flag. Media hosting is not offered: the call still succeeds and hostedUrl is null. |
| `limit` | integer | no | 10 | 1–60 | Maximum audio minutes you agree to pay for (1-60, default 10). The price is charged per started minute, capped here. |

Unknown fields are rejected with `400 invalid_input`. The routing controls `preferLatencyUnderMs` and `maxCredits` may be sent in the same JSON body.

## Output

When `output.found` is `true`, `output.data` has this shape:

| Field | Type | Description |
|---|---|---|
| `id` | string \| null | TikTok video id |
| `url` | string | Video URL |
| `ownerUsername` | string \| null | Creator @handle when the source provides it |
| `thumbnailUrl` | string \| null | Cover image URL (signed, expires) |
| `language` | string \| null | Detected spoken language (ISO 639-1 or name, as the recognizer reports it) |
| `durationSeconds` | number \| null | Audio length in seconds |
| `transcript` | string | Full transcript text (empty for silent videos) |
| `segments` | object[] |  |
| `segments[].startSeconds` | number \| null | Segment start, seconds from the beginning of the video |
| `segments[].endSeconds` | number \| null | Segment end, seconds from the beginning of the video |
| `segments[].text` | string |  |
| `segments[].speaker` | string \| null | Always null: Whisper does no diarization |
| `words` | object[] \| null | Per-word timings when wordTimestamps=true |
| `words[].startSeconds` | number \| null |  |
| `words[].endSeconds` | number \| null |  |
| `words[].text` | string |  |
| `source` | enum | asr = our speech-to-text; captions = TikTok caption track; captions_or_asr = the source does not say which |
| `hostedUrl` | string \| null | Always null: media hosting is not offered (AnyAPI hostVideo parity field) |
| `bytes` | integer \| null | Always null (hosting not offered) |
| `expiresUtc` | string \| null | Always null (hosting not offered) |

When the thing you asked about does not exist (or a search matches nothing) the call still succeeds: `output.found` is `false`, `output.data` is `null` and `output.reason` says why (`not_found`, `private`, `no_results`, …). Misses are free unless the notes below say misses are billed.

## Example request

```bash
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"}'
```

## Example response

_Values are placeholders that follow the output schema; `credits` is what this call would cost at the usual price._

```json
{
  "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

- Usual price: 3 credits per call
- Price ceiling: up to 33 credits if a call is retried elsewhere. A quote’s `maxCredits` is the most a given call can cost; the `maxCredits` routing control caps it per call
- Live 30-day status, success rate, uptime and latency: `GET https://api.primaryapi.com/v1/status/apis?sku=tiktok.video_transcript_full`

## Errors to handle

`invalid_input`, `unauthorized`, `insufficient_balance`, `key_limit_reached`, `trial_cap_reached`, `forbidden`, `not_found`, `idempotency_conflict`, `rate_limited`, `all_sources_failed`, `service_unavailable`, `timeout`. See https://primaryapi.com/docs/errors.

## Notes

Billed per started minute (min 1, max `limit`). Third-party creator audio: transcripts are derivative processing, no media is stored.

