PineDrama Transcript API | Timestamps & Opening Hooks

PineDrama Transcript API

Extract PineDrama short drama transcripts with timestamps, speaker labels, and opening hooks. Transcribe an entire series or selected episodes, then collect structured JSON for dialogue search, content research, and creative analysis.

Each successful episode includes its full transcript and the first spoken sentence as an opening hook. Process up to 10 series or 1,000 unique episodes per run.

🔗 Explore more PineDrama Actors

Build your PineDrama workflow, from finding a series to collecting episodes, video URLs, and transcripts.

Actor	What you can do
🔎 PineDrama Search Scraper	Find short dramas and series IDs by keyword.
📖 PineDrama Drama Details Scraper	Get series information, episode lists, and first-episode IDs.
📋 PineDrama Episodes Scraper	Collect episode IDs and their order for a series.
▶️ PineDrama Video URL Scraper	Get playable episode URLs and available video details.
✨ PineDrama Recommendations Scraper	Discover similar short dramas from a series ID.

What can you do with PineDrama transcripts?

• Build a searchable library of short drama dialogue.
• Compare opening lines, suspense, and conflict across episodes.
• Find spoken passages and their timestamps for clip research.
• Organize transcripts by series and episode.
• Collect results through Apify Console or the API for your own workflows.

How to get started

1. Choose full-series transcription or selected episodes.
2. Enter the relevant PineDrama IDs using one of the examples below.
3. Review the price and set your maximum run spend.
4. Start the Actor and open the results when the run finishes.

Use PineDrama Search to find series IDs and PineDrama Episodes to find episode IDs. You can also explore PineDrama Recommendations to discover related series.

Input examples

Transcribe a full series

{
  "collectionIds": ["7675963864189735957"]
}

Supply up to 10 unique series IDs. The combined series must contain no more than 1,000 unique episodes. Full-series mode uses the series title to help recognize dialogue.

Transcribe selected episodes

{
  "episodes": [
    {
      "collection_id": "7675963864189735957",
      "video_id": "7675963864189752341"
    }
  ]
}

Supply up to 1,000 unique episodes. Each episode needs both its series ID (collection_id) and episode ID (video_id). This mode transcribes the audio without additional series-title context.

Choose either collectionIds or episodes in one run. IDs must be strings containing 1–20 digits. Duplicate entries are removed before input limits are checked. Example IDs show the required format; availability can change.

Transcript output

The Dataset contains one row per unique episode. Results include:

Field	What you receive
seriesId, videoId	PineDrama series and episode identifiers. seriesId corresponds to the input collection_id.
episodeNumber, title, sourceSeriesIds	Available episode number, series title, and associated series IDs.
durationSeconds, language	Audio duration and the detected language when available.
transcript	Recognized dialogue for the episode.
hook	The first non-empty recognized sentence in audio order.
hookStartSeconds, hookEndSeconds	Opening-hook timestamps when they can be determined reliably.
segments	Dialogue segments with start and end times, text, and speaker labels.
wordsJsonUrl	A link to word-level transcript data when available.
status, errorCode	Whether the episode succeeded, failed, or remains pending, with an error code when relevant.
generatedAt	When the transcript was originally generated.

A shortened, fictional example:

{
  "seriesId": "7675963864189735957",
  "videoId": "7675963864189752341",
  "episodeNumber": 1,
  "title": "Example Drama",
  "durationSeconds": 120,
  "language": "en",
  "transcript": "Why are you here? I came to find you.",
  "hook": "Why are you here?",
  "hookStartSeconds": 1.2,
  "hookEndSeconds": 2.8,
  "segments": [
    {
      "start": 1.2,
      "end": 2.8,
      "text": "Why are you here?",
      "speakerId": "speaker_0"
    }
  ],
  "status": "succeeded",
  "errorCode": null
}

The Actor delivers JSON transcripts. It does not generate SRT or VTT subtitle files. Speaker labels distinguish voices within an episode; they do not identify characters or match people across episodes. Fields that are unavailable may be null.

Opening hook extraction

Collect the first spoken sentence alongside each full transcript to build an opening-line library, compare storytelling approaches, and research promotional clips. Hook extraction is included in the episode price.

The hook reflects recognized dialogue. It is not a generated headline, a plot summary, or a fixed three-second excerpt. Opening silence is skipped. When an exact sentence boundary cannot be timed reliably, its ending timestamp may be null.

Pricing

The same event prices apply to all Apify plans, including Free.

Charge	Price
Successful episode transcript, including the first 180 seconds	$0.01499 per episode — $14.99 per 1,000 episodes
Each started minute beyond 180 seconds	$0.006 per additional minute
Failed, speech-free, pending, or budget-skipped episode	No successful-result event charge

Full transcripts, opening hooks, and available timestamps are included. A 4-minute-20-second episode costs $0.01499 + 2 × $0.006 = $0.02699 in event charges. Full-series requests are priced per successful episode.

Apify platform usage is charged separately, including compute, storage, and proxies. Check the active prices in the Pricing tab before starting a run.

Duplicate episode IDs within one uninterrupted run produce one result and one set of result charges. Each new run is charged normally for successful results, including episodes processed previously or results that can be reused.

Free-plan accounts can receive up to 10 successful episode results per UTC calendar month. This is a usage cap, not a free-transcription allowance: the event prices above still apply. Successful results from repeat runs count toward the cap.

Limits and result quality

Episodes can be up to 30 minutes long. A very low maximum run spend can cause an episode to be skipped before its duration is known. Input limits, the Free-plan monthly cap, and the maximum run spend are separate limits.

Background music, accents, overlapping speech, and recording quality can affect transcription. Review dialogue and timing before using them in published work. Unavailable episodes return a status and error code; other episodes can continue while budget and quota allow.

If a run is interrupted, completed results remain available in that run. Review its results and charge history before starting another run.

Frequently asked questions

Can I transcribe an entire PineDrama series?

Yes. Use collectionIds for up to 10 series, with a combined maximum of 1,000 unique episodes. Each successful episode has its own result and price.

Do I need both IDs for a selected episode?

Yes. Each episodes entry requires collection_id and video_id. Use the related Search and Episodes Actors to obtain them.

Are previously processed episodes charged again?

Yes. Each new run charges for successfully delivered episode results at the same price. Duplicate episode IDs within the same uninterrupted run are counted once.

Is this a translation service?

No. The Actor transcribes spoken dialogue; it does not translate transcripts into a requested language.

Support

Maintained by spider_studio, independently of PineDrama. For help, share your run URL through the Issues tab. See the API tab to connect this Actor to your application.