# Video Pacing QA — Frozen Frames, Cut Rate & Dead Air (`fayacuts/video-pacing-qa`) Actor

Automated edit QA for AI-generated and batch-produced videos: frozen frames, slow pans that never cut, cuts per minute, dead air and loudness jumps, each with timestamps and a PASS/FAIL verdict.

- **URL**: https://apify.com/fayacuts/video-pacing-qa.md
- **Developed by:** [Ricardo Faya](https://apify.com/fayacuts) (community)
- **Categories:** Videos, AI
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per usage

This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have.

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

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
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.
Actors are written with capital "A".

## 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.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## Video Pacing QA — Frozen Frames, Cut Rate & Dead Air

Automated **edit QA** for videos you produce in batches — AI-generated lessons, faceless YouTube channels, Shorts factories, course platforms. Paste file URLs; get a **PASS/FAIL verdict with timestamps** for the defects that never raise an error.

### Why this exists

Written by a broadcast editor working since 1998 (two FIFA World Cups). An automated course pipeline produced 41 lessons that passed every log and were unwatchable:

- **3 image changes per minute** — slides with narration;
- a single shot held for **231 seconds**;
- a lesson whose last **54.6 seconds were one frozen frame**, while the generator reported *"209 shots, average 2.34 s"*.

The generator counted the shots it **planned**. Nothing measured what ended up **in the file**. This Actor measures the file.

### What it checks

| Check | What it catches | Default |
|---|---|---|
| **Frozen frames** | pixels that stop moving (stuck render, missing clip, black tail) | fails at 4 s |
| **Longest shot without a visible change** | slow pans/zooms over one still image — they move pixels, so freeze detection **never** fires | fails above 8 s |
| **Visible changes per minute** | "slideshow" pacing | fails below 12/min |
| **Dead air** | seconds with neither voice nor music (a 40 s music bed on a 18 min film) | fails above 1% |
| **Loudness jumps** | level steps between neighbouring 5 s blocks | reported, never fails |

Every threshold is editable.

### Output

One dataset row per video:

```json
{
  "url": "https://example.com/lesson-02.mp4",
  "verdict": "FAIL",
  "findings": [
    "1 frozen stretch(es) of 4s or more — worst 54.6s at 07:14.6.",
    "3 shot(s) longer than 8s without a visible change — longest 54.6s at 07:14.6 (slow pans over a still image land here)."
  ],
  "durationSeconds": 489.2,
  "resolution": "1920x1080",
  "changesPerMinute": 23.5,
  "medianShotSeconds": 2.17,
  "longestShotSeconds": 54.6,
  "longestShotAt": "07:14.6",
  "staticShots": [{ "at": "07:14.6", "seconds": 54.6 }],
  "freezes": [{ "at": "07:14.6", "startSeconds": 434.6, "seconds": 54.6 }],
  "deadAirPercent": 0.2,
  "loudnessJumps": [{ "at": "03:05.0", "deltaDb": -12.4 }]
}
```

The key-value store `OUTPUT` holds the run summary (passed, failed, errors).

### Input notes

- Use **direct file links** (`.mp4`, `.mov`, `.webm`, `.mkv`) — S3, Cloudflare R2, Google Cloud Storage signed URLs and CDN links work. Web pages (YouTube watch URLs, Drive previews) do not.
- A "visible change" is an ffmpeg scene score above the sensitivity (0.3). Two crops of the same image may not count — which is also what a viewer perceives.

# Actor input Schema

## `videos` (type: `array`):

Direct links to video files (.mp4, .mov, .webm, .mkv). Page URLs such as a YouTube watch page are not supported.

## `freezeSeconds` (type: `number`):

A frame that does not change for this long fails. Default 4.

## `maxStaticSeconds` (type: `number`):

Catches slow pans and zooms over a single still image, which never trigger freeze detection. Default 8.

## `minChangesPerMinute` (type: `number`):

Below this the piece reads as slides with narration. Default 12; edited teaching videos typically sit at 20+.

## `maxDeadAirPercent` (type: `number`):

Share of seconds with neither voice nor music. Default 1%.

## `sceneThreshold` (type: `number`):

ffmpeg scene score (0–1). Lower counts subtler changes. Default 0.3.

## `loudnessJumpDb` (type: `number`):

Reports level steps between neighbouring 5-second blocks larger than this. Informational, does not fail the video.

## `maxFileSizeMb` (type: `integer`):

Videos larger than this are skipped with an error instead of downloaded.

## Actor input object example

```json
{
  "videos": [
    {
      "url": "https://www.w3schools.com/html/mov_bbb.mp4"
    }
  ],
  "freezeSeconds": 4,
  "maxStaticSeconds": 8,
  "minChangesPerMinute": 12,
  "maxDeadAirPercent": 1,
  "sceneThreshold": 0.3,
  "loudnessJumpDb": 9,
  "maxFileSizeMb": 2048
}
```

# Actor output Schema

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

One row per video: PASS/FAIL, findings with timestamps, cut rate, freezes and dead air.

## `summary` (type: `string`):

Totals for the whole run (key-value store record OUTPUT).

# 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 = {
    "videos": [
        {
            "url": "https://www.w3schools.com/html/mov_bbb.mp4"
        }
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("fayacuts/video-pacing-qa").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 = { "videos": [{ "url": "https://www.w3schools.com/html/mov_bbb.mp4" }] }

# Run the Actor and wait for it to finish
run = client.actor("fayacuts/video-pacing-qa").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 '{
  "videos": [
    {
      "url": "https://www.w3schools.com/html/mov_bbb.mp4"
    }
  ]
}' |
apify call fayacuts/video-pacing-qa --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,fayacuts/video-pacing-qa"
        }
    }
}
```

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/2VhvksTGlTr7KMu9F/builds/YqDLaBzxae2ndqgSB/openapi.json