# Video Transcript + On-screen Text + Hook & Summary AI (`vidlens/video-understanding`) Actor

TikTok, Instagram Reels, YouTube Shorts or any video URL in, full breakdown out: timestamped transcript, on-screen text (OCR), scene descriptions, first-3-second hook analysis, summary, topics, call to action and optional translation. One call, $0.01 per video.

- **URL**: https://apify.com/vidlens/video-understanding.md
- **Developed by:** [Brain Spice](https://apify.com/vidlens) (community)
- **Categories:** AI, Videos, Social media
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $10.00 / 1,000 video analyzeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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

## Video Understanding — transcript, on-screen text, hook & summary from any short-form video

> 🎁 **Free trial until Nov 20, 2026: your first 5 videos are free** (no charge for analysis or translation). After that, $0.01 per video.

Paste a TikTok, Instagram Reel, YouTube Short (or 1,000+ other sites) link and get **everything that is in the video** as clean JSON — not just the speech.

| You get | Details |
|---|---|
| 🗣️ Speech transcript | Timestamped segments, 99 languages auto-detected (works on videos **without captions**) |
| 🔤 On-screen text (OCR) | Text overlays, captions, product names read from frames |
| 🎬 Scene descriptions | One line per sampled frame — what is actually shown |
| 🪝 First-3-second hook | What grabs attention at the start, from the opening frame + first words only |
| 📝 Summary, topics, CTA | 3–5 bullet summary, keywords, call-to-action |
| 🌐 Translation (optional) | Transcript translated with timestamps kept (ja, es, de, fr, pt-BR, zh, ko …) |

### Why this one

- **All-in-one.** Most actors return only the transcript. Marketers and AI agents need the hook, the text on screen and the visuals too — one run, one row.
- **Accurate.** Speech model benchmarked at **2.2% word error rate** on 1 hour of human-captioned talks.
- **Cheap.** You only pay for videos that were analyzed successfully. Failed or private videos are free.
- **Fast.** A 60-second TikTok takes about 30–45 seconds end to end.

### Input

```json
{ "videoUrls": ["https://www.tiktok.com/@user/video/123"], "translateTo": "ja", "frames": 6 }
```

### Output (one item per video)

```json
{
  "source": "https://www.tiktok.com/@cookingwithkatiecross/video/7490716178357243182",
  "status": "ok",
  "language": "en",
  "duration": 61.4,
  "hook": "A hand holds a plate of Mexican cheesy chicken and rice while queso is poured over it; overlay text 'Mexican Cheesy Chicken & Rice'; speaker: 'Tonight for supper we're making…'",
  "summary": ["…"], "topics": ["…"], "call_to_action": "",
  "transcript": [{"start": 0.0, "end": 4.9, "text": "Tonight for supper we're making…"}],
  "frames": [{"t": 0.5, "on_screen_text": "Mexican Cheesy Chicken & Rice", "scene": "…"}],
  "translation": {"lang": "ja", "text": "[0s] 今夜の夕食は…"}
}
```

### Use cases

- Competitor & trend research: why do top videos in a niche work? (hooks, on-screen text, CTAs)
- Content repurposing: video → blog post / caption / script
- Feeding AI agents and RAG pipelines with what is said **and shown** in videos
- Localization: translated, timestamped transcripts

### Notes

- Public videos only. Max 20 minutes per video.
- Works great with the Apify MCP server, so Claude / ChatGPT agents can call it directly.

### More tools from Brain Spice

- [Video Transcript + On-screen Text + Hook & Summary AI](https://apify.com/vidlens/video-understanding) — TikTok / Reels / Shorts breakdown, $0.01 per video
- [Podcast & Audio Transcript with Speakers, Chapters, SRT](https://apify.com/vidlens/podcast-transcript-speakers-chapters) — who said what + chapters, $0.008 per minute
- [YouTube Comments AI Analyzer](https://apify.com/vidlens/youtube-comments-ai-analyzer) — sentiment, viewer questions, content ideas, $1 per 1,000 comments

### Use it from code, n8n, Make or an AI agent

**API (one call, waits for the result):**

```bash
curl -X POST "https://api.apify.com/v2/acts/vidlens~video-understanding/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videoUrls": ["https://www.tiktok.com/@user/video/123"]}'
```

**Python:**

```python
from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("vidlens/video-understanding").call(run_input={"videoUrls": ["https://www.tiktok.com/@user/video/123"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)
```

- **n8n:** use the *Apify* node → "Run actor and get dataset", actor `vidlens/video-understanding`.
- **Make / Zapier:** use the Apify app → "Run an Actor", then "Get dataset items".
- **AI agents (Claude, ChatGPT, Cursor):** available through the Apify MCP server (`https://mcp.apify.com`) — add `vidlens/video-understanding` as a tool.

# Actor input Schema

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

Links to individual videos (TikTok, Instagram Reels, YouTube Shorts/videos, X, Facebook, Vimeo and 1,000+ sites). Max 20 minutes per video.

## `translateTo` (type: `string`):

Language code such as ja, es, de, fr, pt-BR, zh, ko. Leave empty for no translation.

## `frames` (type: `integer`):

How many evenly spaced frames to read for on-screen text and scenes (plus the opening frame).

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.tiktok.com/@cookingwithkatiecross/video/7490716178357243182"
  ],
  "translateTo": "",
  "frames": 6
}
```

# Actor output Schema

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

One item per video: transcript segments, on-screen text and scene per frame, first-3-second hook, summary, topics, call to action, optional translation, and status/error.

# 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.tiktok.com/@cookingwithkatiecross/video/7490716178357243182"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("vidlens/video-understanding").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.tiktok.com/@cookingwithkatiecross/video/7490716178357243182"] }

# Run the Actor and wait for it to finish
run = client.actor("vidlens/video-understanding").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.tiktok.com/@cookingwithkatiecross/video/7490716178357243182"
  ]
}' |
apify call vidlens/video-understanding --silent --output-dataset

```

## MCP server setup

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

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/p1oIVoBKu2HIjcNhP/builds/MpVf8dIU5srkvTDqD/openapi.json