Operated by Sourcelane✓ verified
Analyzes short-form videos (Instagram Reels and TikTok) to reverse-engineer why a clip engages viewers by extracting structured, keyword-rich analysis: verbatim opening hooks and classified hook types and delivery modes; timestamped on-screen text overlays merged into searchable phrases and combined transcripts of overlays; detected calls-to-action with timings and counts; a segment-by-segment, timestamped content structure (e.g., hook → problem → solution → proof → CTA); edit-pacing metrics (scene changes, cuts per minute) and production format signals (talking head, voiceover, music); content-type classification and topic keyword extraction; post metadata and engagement metrics; plus a full verbatim transcript. Outputs are produced as structured records for sorting, filtering and downstream analysis and support videos up to 150 MB.
Verified Sep 28, 12:10 AM
$0.10
per video
Up to 10 per call. Only pay for results returned; failed calls are refunded.
| 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://cool-puffin-608.convex.site/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"short-video-hook-analyzer","params":{"videoUrls":["https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"]},"maxResults":10}'Request params
| Field | Type | Required | Description |
|---|---|---|---|
videoUrls | array | required | Instagram reel or TikTok video URLs to analyse, up to 50 per run. Both platforms can be mixed in one run. |
language | string | optional | ISO 639-1 code of the spoken language, e.g. 'en' or 'es'. Leave as 'auto' to detect it automatically. |
includeTranscript | boolean | optional | Include the complete verbatim transcript of the spoken audio alongside the creative analysis. |
Each result contains
| Field | Type | Description |
|---|---|---|
inputUrl | string | Input Url |
platform | string | Platform |
videoId | string | Video Id |
postUrl | string | Post Url |
username | string | Username |
fullName | string | Full Name |
caption | string | Caption |
postedAt | string | Posted At |
durationSeconds | integer | Duration Seconds |
likeCount | integer | Like Count |
commentCount | integer | Comment Count |
playCount | integer | Play Count |
shareCount | integer | — |
engagementRate | number | — |
language | string | — |
hookText | string | — |
hookDeliveredAs | string | — |
hookType | string | — |
hookDurationSeconds | integer | — |
hookAnalysis | string | — |
onScreenText | array | — |
onScreenTextCombined | string | — |
transcript | null | — |
ctas | array | — |
ctaCount | integer | — |
structure | array | — |
sceneChanges | integer | — |
cutsPerMinute | number | — |
hasVoiceover | boolean | — |
hasMusic | boolean | — |
hasBurnedInCaptions | boolean | — |
isTalkingHead | boolean | — |
contentType | string | — |
topics | array | — |
Pick your tool and connect in under a minute. Then just ask — for example: “Transcribe this video and give me timestamps for every product mention: <url>”
Connect Claude
Web, desktop and mobile. Paste one URL.
Adds the Sourcelane MCP server with your key as a header.
claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/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://cool-puffin-608.convex.site/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://cool-puffin-608.convex.site/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://cool-puffin-608.convex.site/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://sourcelane-amber.vercel.app/openapi.jsonOne POST. Pass maxResults to cap cost.
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":"short-video-hook-analyzer","params":{"videoUrls":["https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"]},"maxResults":10}'Wrap the REST call as a tool, or point an MCP client at the endpoint.
import requests
res = requests.post(
"https://cool-puffin-608.convex.site/v1/call",
headers={"Authorization": "Bearer sl_live_your_agent_key"},
json={
"listing": "short-video-hook-analyzer",
"params": {"videoUrls":["https://www.tiktok.com/@tiktokcreators/video/7630922277026090254"]},
"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…