# Viral Clip Finder - Podcast Clips & YouTube Shorts Moments (`martin10291/youtube-shorts-clip-finder`) Actor

Finds the best moments in long YouTube videos for Shorts, TikTok and Reels. Returns start/end timestamps, virality score, hook line, title, hashtags and SRT subtitles. No AI keys, no downloads.

- **URL**: https://apify.com/martin10291/youtube-shorts-clip-finder.md
- **Developed by:** [Martin Petrov](https://apify.com/martin10291) (community)
- **Categories:** Videos, Social media, AI
- **Stats:** 2 total users, 1 monthly users, 80.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $3.50 / 1,000 results

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## YouTube Shorts Clip Finder - Viral Moments, Timestamps & Captions

Turn long YouTube videos (podcasts, interviews, streams, webinars, talks) into **ready-to-cut Shorts, TikToks and Reels**. For every video this actor finds the strongest moments and returns **start/end timestamps, a virality score, the hook line, a suggested title, hashtags, the clip transcript and SRT subtitles**.

No downloads and no AI keys: it reads the public captions, so it is fast and cheap. Perfect for clippers, agencies, podcasters and creators who repurpose long content.

### What you get for each clip

| Field | Example |
|---|---|
| `startSeconds` / `endSeconds` | `612.4` / `655.0` |
| `viralityScore` | `8.7` (1-10) |
| `hook` | "Why did you quit your job at Google after only two years?" |
| `suggestedTitle` | "Why did you quit your job at Google after only two years?" |
| `suggestedHashtags` | `["#podcast", "#startup", "#google"]` |
| `transcript` | full text of the clip |
| `srt` | subtitles timed from 0, ready for CapCut / Premiere / DaVinci |
| `clipUrl` | link that opens the video at the clip start |
| `whyThisClip` | "strong opening line, concrete numbers, ends on a complete thought" |

### How the moments are chosen

Every 15-180 s window that starts on a sentence is scored on what makes short clips work:

- a **strong first line** (question, numbers/money, curiosity words) - the first 2 seconds decide retention;
- **concrete numbers**, emotion and a twist/contrast;
- a **complete ending** (no cut mid-sentence) and a fast, clear speaking pace;
- intros ("welcome back to the show"), ads and topic changes are skipped automatically.

Clips never overlap and are sorted by score.

### Input

| Field | Description |
|---|---|
| `videoUrls` | Videos, playlists or channels (@handle) |
| `clipsPerVideo` | Best moments per video (default 5) |
| `minClipSeconds` / `maxClipSeconds` | Clip length range (default 20-55 s, Shorts-ready) |
| `minViralityScore` | Skip weaker moments |
| `hashtags` | Your hashtags added to every suggestion |
| `includeSrt` | Add SRT subtitles (default on) |
| `languages` | Preferred caption languages |

### Example output (illustrative)

```json
{
  "videoTitle": "Steve Jobs' 2005 Stanford Commencement Address",
  "rank": 1,
  "startSeconds": 541.2,
  "endSeconds": 589.0,
  "durationSeconds": 47.8,
  "viralityScore": 9.4,
  "hook": "Remembering that I'll be dead soon is the most important tool I've ever encountered.",
  "suggestedHashtags": ["#motivation", "#stevejobs", "#life"],
  "clipUrl": "https://www.youtube.com/watch?v=UF8uR6Z6KLc&t=541s"
}
```

### Pricing

Pay per result: you only pay for clips saved to the dataset. Videos without captions are skipped for free.

### FAQ

**Does it download or cut the video?** No. It returns the exact timestamps and subtitles; cut the clip in any editor or with ffmpeg (`ffmpeg -ss START -to END`).

**Which videos work best?** Talking content with captions: podcasts, interviews, keynotes, streams. Music videos have no useful transcript.

**Can I run it on a schedule?** Yes - point it at a channel and schedule it daily to get fresh clip ideas from every new episode.

### Legal

This actor reads publicly available captions. Make sure you have the rights or permission to repurpose the content you clip.

# Actor input Schema

## `videoUrls` (type: `array`):

Podcasts, interviews, streams or talks: a video URL or ID, a playlist URL, or a channel URL / @handle (its newest videos are used).

## `clipsPerVideo` (type: `integer`):

How many of the best moments to return for each video.

## `minClipSeconds` (type: `integer`):

Shortest clip to return.

## `maxClipSeconds` (type: `integer`):

Longest clip. 55-60 for YouTube Shorts and Reels, up to 180 for TikTok.

## `minViralityScore` (type: `integer`):

Skip weaker moments. 0 returns all requested clips.

## `hashtags` (type: `array`):

Your own hashtags added to every suggestion, e.g. #podcast.

## `includeSrt` (type: `boolean`):

Ready-to-use subtitles for every clip, timed from 0.

## `languages` (type: `array`):

Preferred caption languages, e.g. en, es, de. Falls back to any available language.

## `maxVideosPerSource` (type: `integer`):

How many of the newest videos to take from each playlist or channel.

## `maxItems` (type: `integer`):

Hard limit on how many clips the run saves (and you pay for).

## `proxyConfiguration` (type: `object`):

Apify Proxy is recommended; YouTube often blocks plain server IPs.

## `residentialFallback` (type: `boolean`):

If YouTube blocks the datacenter IP, retry the video through residential proxy.

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.youtube.com/watch?v=UF8uR6Z6KLc",
    "https://www.youtube.com/watch?v=arj7oStGLkU"
  ],
  "clipsPerVideo": 5,
  "minClipSeconds": 20,
  "maxClipSeconds": 55,
  "minViralityScore": 0,
  "hashtags": [],
  "includeSrt": true,
  "languages": [
    "en"
  ],
  "maxVideosPerSource": 5,
  "maxItems": 10,
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "residentialFallback": true
}
```

# Actor output Schema

## `results` (type: `string`):

Items extracted by the Actor.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "videoUrls": [
        "https://www.youtube.com/watch?v=UF8uR6Z6KLc",
        "https://www.youtube.com/watch?v=arj7oStGLkU"
    ],
    "clipsPerVideo": 5,
    "maxItems": 10,
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("martin10291/youtube-shorts-clip-finder").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "videoUrls": [
        "https://www.youtube.com/watch?v=UF8uR6Z6KLc",
        "https://www.youtube.com/watch?v=arj7oStGLkU",
    ],
    "clipsPerVideo": 5,
    "maxItems": 10,
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("martin10291/youtube-shorts-clip-finder").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "videoUrls": [
    "https://www.youtube.com/watch?v=UF8uR6Z6KLc",
    "https://www.youtube.com/watch?v=arj7oStGLkU"
  ],
  "clipsPerVideo": 5,
  "maxItems": 10,
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call martin10291/youtube-shorts-clip-finder --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,martin10291/youtube-shorts-clip-finder"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/il4P4DXrDfqxoP29j/builds/HgVWQ8VM1aFm1fUFE/openapi.json