X Video Subtitle & Caption Transcript Converter: MCP config, n8n workflow and API

{
  "postUrls": [
    "https://x.com/firesidealpha/status/2118737977824395524"
  ],
  "transcriptionMethod": "captions",
  "whisperModel": "base",
  "outputFormat": "segments",
  "includeTweetMetadata": true,
  "includeQuotedVideo": true,
  "segmentGranularity": "segment",
  "includeWordTimestamps": false,
  "enableYtdlpFallback": false
}

---
name: x-video-subtitle-and-caption-transcript-converter
description: "Per-video transcript records with timestamped segments, full transcript text, timestamped text, RAG chunks, SRT/VTT subtitle output and complete post/author metadata. Status records carry a typed errorCode. Runs the Apify Actor nimbryxo-studio/x-video-subtitle-and-caption-transcript-converter. Use when the user needs X (Twitter) data with fields such as type, tweetUrl, tweetId, videoIndex, videoSource, authorUsername and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "nimbryxo-studio/x-video-subtitle-and-caption-transcript-converter"
  store-url: "https://apify.com/nimbryxo-studio/x-video-subtitle-and-caption-transcript-converter"
---

# X Video Subtitle & Caption Transcript Converter

Use this skill to fetch X (Twitter) data with the Apify Actor `nimbryxo-studio/x-video-subtitle-and-caption-transcript-converter` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `postUrls` | array | Post links or bare post IDs that contain a video or GIF. Accepts x.com and twitter.com links, /i/status and /i/web/status links, /video/N links, and bare numeric IDs. Profile links or usernames are accepted too and are treated like profile inputs. |
| `transcriptionMethod` | one of `auto`, `captions`, `ai` | Auto tries the video's built-in captions first and only falls back to Whisper AI when none exist. Captions-only skips videos without captions. AI-only always uses Whisper speech-to-text. |
| `whisperModel` | one of `tiny`, `base`, `small`, `medium`, `large-v2` | Whisper model used for AI transcription. Larger models are more accurate but slower and need more memory (medium and large-v2 need a run memory of at least 4096 MB and 8192 MB respectively). Base is a good balance for most videos. |
| `outputFormat` | one of `segments`, `fullText`, `both`, `srt`, `vtt` | Segments gives timestamped lines, full text gives one transcript string, and both gives both plus SRT and WebVTT text and download links. SRT and WebVTT modes return the subtitle text and a signed download link. |
| `includeTweetMetadata` | boolean | Attach the full post and author metadata (text, counts, bio, followers, quote/repost details) to every row. |
| `includeQuotedVideo` | boolean | When a quote post has no video of its own, transcribe the video of the quoted post. The row keeps the quote post's metadata and records quotedTweetId. |
| `segmentGranularity` | one of `segment`, `sentence`, `word` | Level of the timestamped segments. Segment keeps the raw caption/Whisper cues. Sentence groups real word timings into sentences (or splits cue text, sharing the cue's real time range). |
| `includeWordTimestamps` | boolean | Add per-word start/end times to AI (Whisper) transcript segments. Automatically enabled when Segment granularity is Sentence or Word. Native captions only carry words when X included inline timing markers. |
| `enableYtdlpFallback` | boolean | When the direct HTTP media download or Whisper transcription fails, try yt-dlp (requires ffmpeg). Off by default so runs stay fast, deterministic and HTTP-only. |

Example `input.json` (the Actor's published prefill):

```json
{
  "postUrls": [
    "https://x.com/firesidealpha/status/2118737977824395524"
  ],
  "transcriptionMethod": "captions",
  "whisperModel": "base",
  "outputFormat": "segments",
  "includeTweetMetadata": true,
  "includeQuotedVideo": true,
  "segmentGranularity": "segment",
  "includeWordTimestamps": false,
  "enableYtdlpFallback": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/nimbryxo-studio~x-video-subtitle-and-caption-transcript-converter/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/nimbryxo-studio~x-video-subtitle-and-caption-transcript-converter/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `type`, `tweetUrl`, `tweetId`, `videoIndex`, `videoSource`, `authorUsername`, `authorName`, `language`, `captionSource`, `captionLanguage`, `metadataSource`, `mediaSource`, `transcriptionMethod`, `transcriptAvailable`, `transcriptTweetId`, `quotedTweetId`, `retweetedTweetId`, `wordCount`, `mediaDurationSeconds`, `fullTranscript`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.