Operated by Sourcelane✓ verified
Turn any YouTube video into a written summary, key takeaways, timestamped chapters, key quotes and an optional blog post draft from its transcript - no watching required.
A YouTube-focused video summarization connector that ingests video transcripts (manual or auto-generated) and uses transcript parsing plus large language model summarization to produce structured textual artifacts and metadata: concise-to-long summaries written with specific details (names, numbers, tools, conclusions), 5–8 actionable key takeaways, topic tags, timestamped chapter markers with one-line section summaries that can follow or correct creator chapter breaks, verbatim timestamped quotes, optional long-form blog post drafts, and optional plain-text transcripts; the connector also extracts video metadata such as identifiers, title, channel info, upload date, duration and view counts, supports multilingual output/translation of summaries and non-English transcripts, and is designed to handle long recordings (podcasts, lectures, tutorials) by processing large transcripts and generating per-video structured outputs using an LLM-based pipeline.
Verified Sep 28, 3:56 AM
$0.06
per video
Up to 16 per call. Only pay for results returned; failed calls are refunded.
Research and learning
Digest lectures, conference talks and interviews quickly
Content repurposing
Convert videos into blog posts, newsletters and social threads
Chapter generation
Create or correct timestamped chapters for video descriptions
Competitive monitoring
Summarise new videos from rival channels on a schedule
Knowledge bases
Index a channel’s back catalogue as searchable text
Meeting and webinar notes
Summarise recorded sessions published to YouTube
YouTube video URLs or IDs, one per line.
Language to write the summary in, e.g.
Optional settings
| Window | Uptime | Success rate | p50 | p95 | Calls |
|---|---|---|---|---|---|
| 24h | — | — | — | — | 0 |
| 7d | — | — | — | — | 0 |
| 30d | — | — | — | — | 0 |
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://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"youtube-video-summarizer","params":{"videoUrls":["https://www.youtube.com/watch?v=8jPQjjsBbIc"]},"maxResults":10}'Request params
| Field | Type | Required | Description |
|---|---|---|---|
videoUrls | array | required | YouTube video URLs or IDs, one per line. Up to 50 per run. |
summaryLength | string | optional | How detailed the main summary should be. Key takeaways, chapters and quotes are produced regardless. |
includeChapters | boolean | optional | Produce timestamped chapters with a title and one-line summary each, ready to paste into a video description. |
includeKeyQuotes | boolean | optional | Pull 3-6 verbatim, timestamped quotes worth sharing or citing. |
includeBlogPost | boolean | optional | Also generate a 600-1000 word Markdown blog post based on the video. Slower and uses more model output. |
includeTranscript | boolean | optional | Add the plain-text transcript to each record. |
outputLanguage | string | optional | Language to write the summary in, e.g. English, Spanish, German. Leave empty to match the transcript language. |
languages | array | optional | Caption languages to try, in order of preference (e.g. en, es, de). Manual captions are preferred over auto-generated ones. |
model | string | optional | Language model used to write the summary. |
Each result contains
| Field | Type | Description |
|---|---|---|
inputUrl | string | Input Url |
videoId | string | Video Id |
url | string | Url |
title | string | Title |
channelTitle | string | Channel Title |
channelId | string | Channel Id |
uploadDate | string | Upload Date |
durationSeconds | integer | Duration Seconds |
viewCount | integer | View Count |
transcriptLanguage | string | Transcript Language |
transcriptIsAutoGenerated | boolean | Transcript Is Auto Generated |
transcriptWordCount | integer | Transcript Word Count |
transcriptTruncated | boolean | — |
transcript | null | — |
summary | string | — |
keyTakeaways | array | — |
topics | array | — |
chapters | array | — |
keyQuotes | array | — |
blogPost | null | — |
model | string | — |
promptTokens | integer | — |
completionTokens | integer | — |
proxyUsed | string | — |
status | string | — |
error | null | — |
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. One click, then confirm.
Adds the Sourcelane MCP server with your key as a header.
claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
--header "Authorization: Bearer sl_live_your_agent_key"Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.
{
"mcpServers": {
"sourcelane": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.usesourcelane.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer sl_live_your_agent_key"
}
}
}
}Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).
{
"mcpServers": {
"sourcelane": {
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer sl_live_your_agent_key"
}
}
}
}Save as .vscode/mcp.json. VS Code prompts for your key once.
{
"servers": {
"sourcelane": {
"type": "http",
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer ${input:sourcelane-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "sourcelane-key",
"description": "Sourcelane agent key",
"password": true
}
]
}Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.
https://usesourcelane.com/openapi.jsonOne POST. Pass maxResults to cap cost.
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"youtube-video-summarizer","params":{"videoUrls":["https://www.youtube.com/watch?v=8jPQjjsBbIc"]},"maxResults":10}'Wrap the REST call as a tool, or point an MCP client at the endpoint.
import requests
res = requests.post(
"https://api.usesourcelane.com/v1/call",
headers={"Authorization": "Bearer sl_live_your_agent_key"},
json={
"listing": "youtube-video-summarizer",
"params": {"videoUrls":["https://www.youtube.com/watch?v=8jPQjjsBbIc"]},
"maxResults": 10,
},
timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])—
0 reviews
Leave a review
Loading reviews…