YouTube Channel Transcripts Scraper

YouTube

Operated by Sourcelane✓ verified

A tool to extract full transcripts and timestamped captions for every video from YouTube channels, playlists or individual videos (including Shorts and live streams), producing searchable text plus per-caption timestamps and video metadata. The connector scrapes caption tracks in multiple languages with ordered language preference, detects whether captions are creator-written or auto-generated, and returns full-text transcripts along with segmented caption lines (each with start time and duration) for clip-finding and timestamped quoting. It also collects video-level metadata such as title, channel info, upload date, duration, view and like counts, and provides per-video processing status. Supports limiting or expanding how many videos are fetched, sorting by recency/popularity/age, de-duplicates videos appearing in multiple sources, and operates without requiring a YouTube API key or account login.

Verified Sep 28, 12:10 AM

$0.02

per transcript

Up to 50 per call. Only pay for results returned; failed calls are refunded.

What people use it for

AI knowledge bases & RAG — load a creator's or company's whole back catalogue into your chatbot or vector database
Content research — search what a channel has said about a topic across hundreds of videos
Repurposing — turn a channel's videos into blog posts, newsletters or social threads
Competitor analysis — see which topics, products and talking points a competitor covers
Education & training — build searchable notes from course or lecture playlists
Podcast & interview mining — pull quotes and timestamps from long-form interview channels

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"youtube-channel-transcripts","params":{"sources":["@veritasium"]},"maxResults":10}'

Request params

Field	Type	Required	Description
`sources`	array	required	One per line. Channels: @handle, youtube.com/@handle, /channel/UC…, /c/name or /user/name. Playlists: youtube.com/playlist?list=… or a playlist ID. Single videos or Shorts URLs work too.
`maxVideosPerSource`	integer	optional	How many videos to take from each channel or playlist. 0 = every video (up to 5,000 per source).
`contentType`	string	optional	Which channel tab to read videos from. Ignored for playlists and single videos.
`sortBy`	string	optional	Order in which channel videos are picked before the per-source limit is applied. Popular and Oldest are available on the Videos tab.
`languages`	array	optional	Language codes in order of preference, e.g. en, es, de. The first language with captions is used for each video.
`preferManualCaptions`	boolean	optional	When a video has both creator-uploaded and auto-generated captions, use the creator's. Turn off to always take auto-generated ones.
`includeSegments`	boolean	optional	Add a segments array with start time, duration and text for every caption line. Turn off for smaller exports when you only need the full text.

Each result contains

Field	Type	Description
`source`	string	Source
`sourceType`	string	Source Type
`videoId`	string	Video Id
`url`	string	Url
`title`	string	Title
`channelName`	string	Channel Name
`channelId`	string	Channel Id
`uploadDate`	string	Upload Date
`publishedText`	string	Published Text
`durationSeconds`	integer	Duration Seconds
`viewCount`	integer	View Count
`likeCount`	integer	Like Count
`language`	string	—
`isAutoGenerated`	boolean	—
`transcript`	string	—
`wordCount`	integer	—
`segments`	array	—
`availableLanguages`	array	—
`status`	string	—
`error`	null	—
`scrapedAt`	string	—

Use YouTube Channel Transcripts Scraper from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “Get the transcript of this video and turn it into a blog outline: <url>”

Connect Claude

Web, desktop and mobile. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"youtube-channel-transcripts","params":{"sources":["@veritasium"]},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "youtube-channel-transcripts",
        "params": {"sources":["@veritasium"]},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

Leave a review

Loading reviews…