# YouTube Chapters & Timestamps Generator (`seemuapps/youtube-chapters-generator`) Actor

Generate YouTube-ready chapter timestamps, an SEO video description and tags from any YouTube video's transcript. Paste video URLs, copy the chapters.

- **URL**: https://apify.com/seemuapps/youtube-chapters-generator.md
- **Developed by:** [Seemu Scraping](https://apify.com/seemuapps) (community)
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $50.00 / 1,000 video chapters generateds

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

## YouTube Chapters & Timestamps Generator

Paste YouTube video URLs and get paste-ready chapter timestamps, an SEO-friendly video description and a set of tags for each one. Chapters are built from the video's transcript, so they land where the topic actually changes, and every list follows YouTube's chapter rules.

### What you get

For every video:

- **chaptersText** - the chapter block, ready to paste into your YouTube description:
  ```
  0:00 Why Docker solves the works on my machine problem
  1:37 Images and containers: Docker recipes and runnable instances
  2:54 Installing Docker and preparing your development environment
  3:37 Writing a Dockerfile for a Node.js server
  ```
- **chapters** - the same list as data: **startSeconds**, **timestamp** and **title** for each chapter
- **seoDescription** - a 120-250 word description with your main keyword in the first line
- **descriptionWithChapters** - the description with the chapter block appended, ready to paste in one go
- **tags** - 12-20 search tags, trimmed to fit YouTube's 500-character tag limit
- **existingChapters** and **hasExistingChapters** - the chapters the video already has, so you can compare
- Video details: **videoId**, **url**, **title**, **channelName**, **durationSeconds**, **transcriptLanguage**
- **status** and **error** for every row

### YouTube chapter rules, handled for you

YouTube only shows chapters when the list follows its rules. Every list this tool returns:

- starts at **0:00**
- has at least **3 chapters**
- keeps every chapter at least 10 seconds long (30 seconds by default, you can change it)
- is in time order, with no duplicates and nothing past the end of the video
- uses `m:ss` timestamps, or `h:mm:ss` from the one-hour mark

Timestamps are taken from the transcript line where each new topic starts, so clicking a chapter jumps to the right moment.

### Use cases

- **YouTube creators** - add chapters to new uploads in seconds instead of scrubbing through the timeline
- **Back-catalogue SEO** - add chapters, descriptions and tags to hundreds of older videos so they show up as key moments in Google and YouTube search
- **Podcasts and long interviews** - chapter 2-3 hour episodes so viewers can jump to the guest or topic they want
- **Agencies and editors** - deliver chapters, descriptions and tags for client channels in bulk
- **Course and tutorial makers** - turn lessons into skimmable, step-by-step sections

### How to use

1. Enter one or more **Video URLs** (or video IDs), up to 50 per run.
2. Pick a **Chapter title style**: Concise, Descriptive or Keyword-rich.
3. Optionally change **Minimum chapter length** (default 30 seconds) and **Maximum chapters** (default 15).
4. Leave **Output language** empty to match the video, or type a language such as `Spanish` to translate the chapters, description and tags.
5. Run the tool. Results appear in the **Dataset** tab. Copy **chaptersText** (or **descriptionWithChapters**) straight into YouTube Studio.

### Output example

```json
{
  "inputUrl": "https://www.youtube.com/watch?v=8jPQjjsBbIc",
  "videoId": "8jPQjjsBbIc",
  "url": "https://www.youtube.com/watch?v=8jPQjjsBbIc",
  "title": "How to stay calm when you know you'll be stressed | Daniel Levitin | TED",
  "channelName": "TED",
  "durationSeconds": 741,
  "hasExistingChapters": true,
  "existingChapters": [
    { "startSeconds": 0, "timestamp": "0:00", "title": "The personal crisis" }
  ],
  "chapters": [
    { "startSeconds": 0, "timestamp": "0:00", "title": "Breaking into his own home and forgetting his passport" },
    { "startSeconds": 192, "timestamp": "3:12", "title": "Using a premortem to anticipate what could go wrong" },
    { "startSeconds": 236, "timestamp": "3:56", "title": "Building reliable places for everyday essentials" }
  ],
  "chaptersText": "0:00 Breaking into his own home and forgetting his passport\n3:12 Using a premortem to anticipate what could go wrong\n3:56 Building reliable places for everyday essentials",
  "seoDescription": "Stress management starts before the crisis: neuroscientist Daniel Levitin shows how a premortem can keep stress from clouding important decisions...",
  "descriptionWithChapters": "Stress management starts before the crisis: ...\n\n0:00 Breaking into his own home and forgetting his passport\n3:12 ...",
  "tags": ["stress management", "premortem", "prospective hindsight", "Daniel Levitin", "TED talk"],
  "chapterStyle": "descriptive",
  "transcriptLanguage": "en",
  "transcriptIsAutoGenerated": false,
  "transcriptTruncated": false,
  "model": "openai/gpt-6-luna",
  "status": "success",
  "error": null
}
```

### Pricing

Each video that gets chapters is charged a small base fee plus a per-minute fee for the length of the video, so a 5-minute clip costs a fraction of a 3-hour podcast. Videos without captions, private or removed videos, and videos too short for chapters are reported with an error and are not charged.

### Tips

- **Keyword-rich** titles help chapters appear as "key moments" in Google search. **Concise** titles read best on mobile.
- For long podcasts, raise **Minimum chapter length** to 120-300 seconds to get fewer, bigger sections.
- A video must be at least 3 x the minimum chapter length long (90 seconds at the default). Lower the minimum to 10-20 seconds for short videos.
- If the video's captions are in a language you want to skip, list the languages to use under **Transcript languages**.

### FAQ

**Does it work on videos without captions?**
No. Chapters are built from the video's manual or auto-generated captions. Videos with captions turned off return a row with an error and are not charged.

**Does it work on long videos?**
Yes. The default model reads the full transcript in one pass, so a 3-hour podcast gets chapters that cover the whole episode.

**My video already has chapters. Why run it?**
The original chapters are returned in **existingChapters** so you can compare. Many creators use this to tighten vague chapter titles or add search keywords.

**Can I get chapters in another language?**
Yes. Set **Output language** to any language name, for example `German`. Chapter titles, description and tags are all written in that language.

# Actor input Schema

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

YouTube video URLs or 11-character video IDs, one per line. Up to 50 per run. The video needs captions (manual or auto-generated).

## `chapterStyle` (type: `string`):

How chapter titles are written. Keyword-rich leads each title with the phrases viewers search for, which helps chapters appear as key moments in Google and YouTube search.

## `minChapterSeconds` (type: `integer`):

Shortest allowed chapter. YouTube requires at least 10 seconds per chapter; 30-60 seconds reads better for most videos.

## `maxChapters` (type: `integer`):

Upper limit on chapters per video. YouTube requires at least 3. The count scales with video length up to this limit.

## `outputLanguage` (type: `string`):

Language for chapter titles, description and tags, e.g. English, Spanish, German. Leave empty to match the video's language.

## `generateDescription` (type: `boolean`):

Also write a 120-250 word YouTube description with the main keyword in the first line, plus a paste-ready version with the chapters appended.

## `generateTags` (type: `boolean`):

Also suggest 12-20 YouTube tags, trimmed to fit YouTube's 500-character tag limit.

## `transcriptLanguages` (type: `array`):

Optional caption language codes to use, in order of preference (e.g. en, es). Leave empty to use the video's own spoken language automatically.

## `model` (type: `string`):

Language model that reads the transcript and writes the chapters. The default handles very long videos in one pass.

## `proxyMode` (type: `string`):

How transcripts are fetched. Auto tries the free routes first, then a backup transcript source, and only then residential proxy.

## Actor input object example

```json
{
  "videoUrls": [
    "https://www.youtube.com/watch?v=8jPQjjsBbIc"
  ],
  "chapterStyle": "descriptive",
  "minChapterSeconds": 30,
  "maxChapters": 15,
  "generateDescription": true,
  "generateTags": true,
  "model": "openai/gpt-6-luna",
  "proxyMode": "auto"
}
```

# Actor output Schema

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

One record per video: inputUrl, videoId, url, title, channelName, durationSeconds, hasExistingChapters, existingChapters, chapters (startSeconds, timestamp, title), chaptersText, seoDescription, descriptionWithChapters, tags, chapterStyle, transcriptLanguage, transcriptIsAutoGenerated, transcriptTruncated, model, 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.youtube.com/watch?v=8jPQjjsBbIc"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("seemuapps/youtube-chapters-generator").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=8jPQjjsBbIc"] }

# Run the Actor and wait for it to finish
run = client.actor("seemuapps/youtube-chapters-generator").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=8jPQjjsBbIc"
  ]
}' |
apify call seemuapps/youtube-chapters-generator --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,seemuapps/youtube-chapters-generator"
        }
    }
}
```

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/Dw2MPfS0Q2irSuirY/builds/Sf0ecNk7xfY134yUE/openapi.json