YouTube Transcript Extractor & API — bulk channels, playlists & search, RAG-ready chunks

Get transcripts for an entire YouTube channel, playlist, or search query in one run — not one video at a time. Every video comes back as a full transcript, timestamped caption segments, and LLM-ready chunks (configurable size and overlap, each with a deep link at …&t=123s) you can load straight into a vector database, a RAG pipeline, n8n, or LangChain.

$2.00 per 1,000 videos. Chunking is included — the chunk event is billed at $0.01 per 1,000 chunks, which is rounding error. Videos with no captions are reported and never charged. No platform-usage surcharge.

Should you use this, or do it yourself?

An honest comparison, because the right answer is sometimes "not this":

Option	Good for	The catch
yt-dlp	Free, one channel, on your own machine	You handle video enumeration, rate limits, retries, parsing and chunking yourself; YouTube throttles datacenter IPs hard
youtube-transcript-api (Python)	Free, a few hundred videos, inside your own code	Same throttling problem at scale; no channel expansion, no chunking, you supply proxies
This Actor	A whole channel/playlist/search in one call, chunked for RAG, callable as an API or MCP tool with no infrastructure	You pay $2 per 1,000 videos
Whisper / ASR services	Videos with no captions at all	Far slower and more expensive per hour of audio

If you are transcribing fifty videos once, use yt-dlp. If you are ingesting a 500-video channel into a vector store on a schedule and you do not want to own the proxy and retry problem, that is what this is for.

What you get

For each video:

• transcript — the full plain-text transcript
• segments — raw caption segments with start and duration (optional)
• chunks — overlapping text windows with startSec / endSec / approxTokens, ready for embeddings
• metadata: videoId, title, channel, url, language, isGenerated, durationSec, wordCount, chunkCount

Choose one item per video (default), one item per chunk (ideal for vector DBs — every row is a chunk with a deep link), or both.

Input

Field	What it does
startUrls	Any mix of video URLs, channel URLs (https://www.youtube.com/@handle/videos), or playlist URLs
searchQueries	YouTube searches; top results are transcribed
maxVideosPerSource	Cap per channel / playlist / query (default 25)
languages	Preferred language codes in order, e.g. ["en", "es"]. Manual captions are preferred over auto-generated; falls back to whatever exists
outputMode	video, chunks, or both
chunkSizeTokens / chunkOverlapTokens	Chunk geometry (default 500 / 50). Set size to 0 to skip chunking
includeSegments	Include raw timestamped segments in video items
proxyConfiguration	Apify residential proxy recommended for large runs

Example input

{
  "startUrls": [{ "url": "https://www.youtube.com/@lexfridman/videos" }],
  "maxVideosPerSource": 50,
  "languages": ["en"],
  "outputMode": "chunks",
  "chunkSizeTokens": 400,
  "chunkOverlapTokens": 40
}

Output example (one item per video)

{
  "videoId": "dQw4w9WgXcQ",
  "title": "Rick Astley - Never Gonna Give You Up",
  "channel": "Rick Astley",
  "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
  "language": "en",
  "isGenerated": false,
  "durationSec": 212,
  "wordCount": 371,
  "chunkCount": 1,
  "status": "ok",
  "transcript": "We're no strangers to love ...",
  "chunks": [{ "chunkIndex": 0, "text": "We're no strangers to love ...", "startSec": 18.6, "endSec": 211.9, "approxTokens": 494 }]
}

Pricing

Pay per event, no platform-usage surcharge:

• video — $2.00 per 1,000 videos successfully transcribed ($1.40 per 1,000 on Business plans)
• chunk — $0.01 per 1,000 chunks; chunking is effectively free

A 100-video channel at ~10 chunks per video costs about $0.21. Videos without captions cost nothing.

Use with AI agents and automations

• MCP: callable as a tool from Claude, ChatGPT, Cursor and any MCP client through Apify's MCP server — an agent can fetch a whole channel's transcripts without a human in the loop.
• n8n / Make / Zapier: use the Apify node and read the dataset.
• API: POST https://api.apify.com/v2/acts/agentbuilt~youtube-transcript-bulk/run-sync-get-dataset-items?token=…

Limits and honesty notes

• Only videos that have captions (manual or auto-generated) can be transcribed. Videos without captions are returned with status: "no_transcript" and are not charged. Audio transcription (Whisper) is planned as an optional add-on.
• YouTube rate-limits aggressive scraping. For runs over ~200 videos, keep the default residential proxy on.
• Member-only, private, or age-restricted videos cannot be transcribed.

About this Actor

Built and maintained by agentbuilt (https://agentbuilt.dev), an AI-operated studio: the code, docs and support are handled by an AI agent, with a human owner accountable for the account. Report issues in the Issues tab — they are triaged daily.