YouTube Shorts Clip Finder

YouTube

Operated by Sourcelane✓ verified

A tool that analyzes long-form YouTube video transcripts with timestamps to identify and rank short-form clip candidates suitable for Shorts, Reels, and TikToks. It locates exact cut points (start/end seconds and timestamp formats), extracts the spoken opening line verbatim as a hook, and generates publication-ready metadata including a suggested title, caption, platform-tailored hashtags, a brief rationale for attention retention, and a virality score. Outputs are structured per clip (ranked best-first) and include clip duration, a transcript excerpt for verification, a URL that opens the source video at the clip start, a paste-ready clip reference for automated cutting, and source video context metadata such as title, channel, upload date, duration, and view count. The connector uses timestamped captions/transcripts to ensure picks correspond to actual spoken moments and filters overlapping candidates to produce discrete, non-overlapping clips.

Verified Sep 28, 12:11 AM

$0.05

per video

Up to 20 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Repurposing a back catalogue: extract Shorts/Reels/TikToks from podcasts, interviews, and lectures
Podcast clip production: provide exact in/out points and ready text for editors
Agency workflows: process batches of client long-form videos and deliver ranked clip sheets
Competitor teardown: identify moments in rival videos likely to perform as short-form content
Newsletter and social scheduling: create multiple posts from a single long-form upload

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-shorts-clip-finder","params":{"videoUrls":["https://www.youtube.com/watch?v=8jPQjjsBbIc"]},"maxResults":10}'

Request params

Field	Type	Required	Description
`videoUrls`	array	required	Long-form YouTube video URLs or IDs, one per line. Up to 20 per run.
`clipsPerVideo`	integer	optional	How many clip candidates to return for each video, best first.
`minClipSeconds`	integer	optional	Shortest clip to return.
`maxClipSeconds`	integer	optional	Longest clip to return. Shorts, Reels and TikTok all accept up to 60 seconds comfortably.
`platform`	string	optional	Shapes the caption and hashtag style of each suggestion.
`includeTranscriptExcerpt`	boolean	optional	Add the actual spoken words inside each clip window, so you can check the pick before editing.
`outputLanguage`	string	optional	Language for the titles and captions, e.g. English, Spanish. Leave empty to match the video.
`languages`	array	optional	Caption languages to try, in order of preference (e.g. en, es, de).
`model`	string	optional	Language model used to pick the clips.

Each result contains

Field	Type	Description
`inputUrl`	string	Input Url
`videoId`	string	Video Id
`videoUrl`	string	Video Url
`videoTitle`	string	Video Title
`channelTitle`	string	Channel Title
`channelId`	string	Channel Id
`uploadDate`	string	Upload Date
`videoDurationSeconds`	integer	Video Duration Seconds
`viewCount`	integer	View Count
`rank`	integer	Rank
`startSeconds`	integer	Start Seconds
`endSeconds`	integer	End Seconds
`startTimestamp`	string	—
`endTimestamp`	string	—
`clipDurationSeconds`	integer	—
`title`	string	—
`hook`	string	—
`caption`	string	—
`hashtags`	array	—
`whyItWorks`	string	—
`viralityScore`	integer	—
`transcriptExcerpt`	string	—
`watchUrl`	string	—
`clipRange`	object	—
`platform`	string	—
`model`	string	—
`proxyUsed`	string	—
`status`	string	—
`error`	null	—

Use YouTube Shorts Clip Finder 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-shorts-clip-finder","params":{"videoUrls":["https://www.youtube.com/watch?v=8jPQjjsBbIc"]},"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-shorts-clip-finder",
        "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"])

Reviews

—

0 reviews

Leave a review

Loading reviews…