YouTube caption scraper in n8n
Get timestamped transcripts from YouTube videos in your preferred language, with optional AI transcription for videos that have no captions at all. Returns full text, timed segments, and core video metadata.
What this workflow does
Import it and n8n runs the YouTube Caption & Whisper AI Transcript Extractor Actor on Apify every day at 08:00 with the starter input below. Each row comes back with video id, title, channel name, published at and 27 more. A Google Sheets append is included and stays off until you add your sheet. The only credential it needs is your Apify API token.
Read from the workflow file, built for YouTube Caption & Whisper AI Transcript Extractor version 1.0.3. Updated 2026-11-14.How the rows travel
6 nodes, in the order n8n runs them. The yellow stop is the call to the Apify Actor; the dashed stop is optional.
- Daily trigger Schedule trigger
- Configure input Code
- Run Apify Actor HTTP Request
- Normalize + dedupe Code
- Rows ready No operation
- Google Sheets (optional) Google Sheets, off until you switch it on
Input
The Configure input node holds the starter input. Change it there; every setting the Actor accepts is listed below.
{
"videoUrls": [
"https://www.youtube.com/watch?v=jNQXAC9IVRw"
],
"whisperModel": "tiny",
"proxyCountry": "GB"
}| Setting | Type | Required | Default | What it does |
|---|---|---|---|---|
| mode | string | No | videos | What to scrape: specific videos, a channel's uploads, or a playlist. One of: videos, channel, playlist. |
| videoUrls | array | No | – | YouTube watch URLs, youtu.be short links, Shorts/embed URLs, or plain 11-character video IDs (mode=videos). Duplicate IDs are processed once. |
| channelUrls | array | No | – | Channel URLs or handles (mode=channel), e.g. https://www.youtube.com/@TED, https://www.youtube.com/channel/UC..., or @TED. |
| maxVideosPerChannel | integer | No | 50 | Maximum number of videos to enumerate from each channel (mode=channel). 1-1,000. |
| playlistUrls | array | No | – | Playlist URLs or IDs (mode=playlist), e.g. https://www.youtube.com/playlist?list=PL... or PL.... Every video in the playlist is transcribed. |
| maxVideosPerPlaylist | integer | No | 50 | Maximum number of videos to enumerate from each playlist (mode=playlist). 1-1,000. |
| language | string | No | – | Caption language to fetch. Leave Auto-detect to use the video's original language. 109 choices. |
| includeAutoGenerated | boolean | No | true | Whether to include auto-generated captions when manual captions are not available. |
| useWhisper | boolean | No | true | When YouTube has no transcript (disabled captions, music-only, or blocked), download the audio and transcribe with Whisper AI (faster-whisper, CPU). Adds ~30-180 s per video. |
| whisperModel | string | No | base | Whisper model size to use when useWhisper is enabled. Larger = more accurate but slower and more RAM. 'base' is balanced. One of: tiny, base, small, medium, large-v3-turbo. |
| includeWordTimings | boolean | No | false | Add a wordTimings array with word-level start/end times. Only auto-generated YouTube captions expose word timings; manual captions and AI transcripts do not. |
| maxWhisperMinutes | integer | No | – | Leave unset for the legacy behavior (AI enabled with no length limit). Set to 0 explicitly to disable AI transcription. |
| proxyCountry | string | No | US | Country/region for the proxy IP. Useful if transcripts are geo-blocked in the default US region. 31 choices. |
| outputFormat | string | No | full | How transcript data is included. 'full' = segments and full_text; 'text_only' = full_text only; 'segments_only' = segments only; 'srt' / 'vtt' = ready-to-use subtitle text derived… One of: full, text_only, segments_only, srt, vtt. |
What each row holds
Every field the Actor returns stays in the row (31 in its dataset schema). Normalize + dedupe trims text, drops empty fields and adds _source and _scrapedAt. The main fields:
| Field | What it is |
|---|---|
| video_id | Video id |
| title | Title |
| channel_name | Channel name |
| publishedAt | Published At |
| transcript_language | Transcript language |
| segment_count | Segment count |
| success | Success |
| transcript_available | Transcript available |
| transcript_source | Transcript source |
| accessStatus | Access Status |
| errorCode | Error Code |
| duration_seconds | Duration seconds |
What the first run costs
Each run starts at $0.40 on the Free plan (4 GB of memory), then $0.99 per 1,000 results, plus platform usage.
The Actor lists $0.99 per 1,000 results; its catalogue page breaks the price down by Apify plan. The Apify Free plan includes $5 of usage a month.
The Actor behind it
YouTube Caption & Whisper AI Transcript Extractor: Get timestamped transcripts from YouTube videos in your preferred language, with optional AI transcription for videos that have no captions at all. Returns full text, timed segments, and core video metadata.
The same job from an AI agent
The matching agent skill gives Claude Code, Codex, Cursor and other agents the same Actor, input and fields. Install it in one line:
npx skills add https://scraperfinder.com --skill youtube-caption-and-whisper-ai-transcript-extractor The youTube caption scraper skill, with manual install and run steps
Questions people ask
How do I import this workflow into n8n?
Copy https://scraperfinder.com/n8n/youtube-caption-and-whisper-ai-transcript-extractor.json. In n8n, open a new workflow, click the three-dot menu, choose Import from URL and paste it. Or download the JSON file and use Import from File; both give the same 6 nodes.
Do I need an Apify account?
Yes. The workflow calls the YouTube Caption & Whisper AI Transcript Extractor Actor through the Apify API with your own token, and each run is billed to your Apify account. The Free plan includes $5 of usage a month.
What does a run cost?
Each run starts at $0.40 on the Free plan (4 GB of memory), then $0.99 per 1,000 results, plus platform usage. The Actor's Store page shows the current price.
Can I change what it collects?
Yes: edit the input object in the Configure input node. The Actor takes 14 settings; the table on this page lists each one with its default. Raise maxVideosPerChannel once the first rows look right.
Does it work without Google Sheets?
Yes. The rows wait in the Rows ready node, so you can connect any other node there: a database, Airtable, a webhook or an email. The Google Sheets node is only one option.