YouTube Transcript Extractor: batch, timestamps, RAG-ready chunks

Get the transcript of any YouTube video that has captions. Paste video URLs, IDs or a playlist link and receive clean text, optional timestamped segments, and optional chunks sized for vector databases (each chunk carries its start time and a deep link).

Why use it

• Batch: hundreds of videos in one run, plus playlists (first 100 videos).
• RAG-ready: set chunkChars (for example 1000) and get chunks cut at natural pauses and sentence ends, with startSeconds, a &t= link for citations, and textWithContext (title + channel prepended) for embedding. Auto-generated captions have no punctuation, so they are split using word-level timing gaps; chunks never exceed 1.4x the target, so they stay inside a 512-token embedding window at ~1500 characters.
• Language control: asks for your language first, falls back to auto-generated or any available track.
• No API key, no cookies, no login.
• You pay only for transcripts delivered: videos without captions are reported in the ERRORS key-value record and are not charged.

Input

Field	Meaning
videos	Video URLs, 11-character IDs, youtu.be/shorts links, or playlist URLs
language	Preferred language code, default en
includeSegments	Add segments with start and duration
chunkChars	0 = off; otherwise approximate chunk size in characters
chunkRows	true = chunks go to a separate dataset, one row per chunk (best for AI agents / MCP: page with limit/offset, project with fields=text,link); the main item gets chunksDatasetId. Still billed per video.

Output example

{ "videoId": "dQw4w9WgXcQ", "title": "...", "channel": "...", "language": "en", "autoGenerated": false,
  "text": "We're no strangers to love ...", "wordCount": 340,
  "chunks": [{ "index": 0, "startSeconds": 18.6, "link": "https://www.youtube.com/watch?v=dQw4w9WgXcQ&t=18s", "text": "...", "textWithContext": "Video title (Channel): ..." }] }

Use cases

LLM and RAG pipelines, video summarization, content repurposing, research datasets, SEO and keyword analysis of video content.

Only public videos with available captions are supported. Respect YouTube's terms and creators' rights when using extracted text.

What is YouTube Transcript Extractor?

YouTube Transcript Extractor downloads the transcript (captions) of YouTube videos in bulk and returns the full text, timestamped segments and pre-split chunks sized for embeddings and RAG pipelines, plus video title, channel, length and views. You can run it from the Apify Console, call it over the API, schedule it, or connect it to Make, Zapier, n8n, Google Sheets and webhooks.

How to use YouTube Transcript Extractor

1. Paste YouTube video URLs or IDs into Videos.
2. Choose a Language (falls back to auto-generated captions when needed).
3. Turn on Include segments if you need timestamps and set Chunk size for RAG.
4. Click Start, then export the transcripts or read them over the API from your LLM app.

How much does it cost?

You pay per video delivered, nothing for compute. Apify subscribers get lower prices:

Plan	Price per video	Per 1,000
Free	$0.0040	$4.00
Bronze	$0.0036	$3.60
Silver	$0.0030	$3.00
Gold	$0.0024	$2.40

Example: 1,000 videos cost about $4.00 on the free plan. The Apify free plan includes $5 of monthly credit, so you can test on real data before paying anything.

Integrations and API

Every run produces a dataset you can download as JSON, CSV, Excel or HTML, or read with the Apify API and the JavaScript/Python clients. The Actor also works as a tool for AI agents through the Apify MCP server.

FAQ

Is it legal? The Actor only reads publicly available pages and does not log in anywhere. You are responsible for how you use the data, including GDPR and the terms of the source site.

Something broke or a field is missing? Open an issue in the Issues tab. I usually reply within a day and fix confirmed bugs quickly.

Need a custom version? Describe it in an issue and I will tell you what is possible.

More Actors from this developer

Actor	What it does
Domain Enricher	Emails, phones, socials and tech stack for a list of company domains
Remote Jobs Aggregator	Remote jobs from 7 job boards in one deduplicated feed
Google News Scraper	Google News articles by keyword or topic, with the real publisher URL
App Reviews Scraper	User reviews from the Apple App Store and Google Play in one dataset
Internet Archive Scraper	Search archive.org, get item metadata, file download links and Wayback Machine snapshots