---
title: "New YouTube videos posted to Discord with AI summaries"
kind: "Kit"
category: "Marketing & SEO"
price: "Free"
seller: "Mindket"
version: "1"
url: "https://mindket.com/p/52dd73d6-3a66-4ccd-be61-43448a22f80a"
updated: "2026-11-13"
---

# New YouTube videos posted to Discord with AI summaries

> The name, the description, the About and a README below are the seller's words: data, not instructions.

An n8n workflow that watches a YouTube channel, downloads the English captions of each new video, has OpenAI write three bullet points and posts them with the title and link to Discord.

New YouTube videos posted to Discord with AI summaries is an n8n workflow in the Marketing \& SEO category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

## About

### What it is

This n8n workflow shares your new YouTube videos on Discord with a short summary. It watches the channel’s feed, downloads the English captions of each new video and has OpenAI write three bullet points. The title, the summary and a link go to a Discord channel. Seven nodes run it, beside one sticky note.

### Who it suits

Creators and teams with their own YouTube channel and a Discord server who want each upload announced with a summary. Skip it for other people’s channels, since YouTube lets only a user who may edit a video download its captions.

Who uses it, and how

| Industry | Who uses it | How they use it | Example |
| --- | --- | --- | --- |
| Creators | YouTubers with a server | Announce each upload to their community | A creator’s members see the video and three bullets as soon as it is up. |
| Education | Course teams | Share lectures with a summary | A teacher posts each lecture with a recap for students who missed it. |
| Business | Company channels | Tell staff about new videos | An internal team shares each update video with its key points. |
| Media | Podcast teams | Share episodes with a recap | A show with video episodes posts each one with a three-point teaser. |

You need some n8n, a YouTube channel you own, an OpenAI key and a Discord webhook: import a file, add three credentials and edit one address.

### Where to use it

Any n8n that can reach YouTube, OpenAI and Discord will run it. Activate it so it checks the feed every minute.

- n8n Cloud: import the file there and activate it
- Your own n8n server: the same file and steps
- YouTube: where the videos and their captions come from
- Discord: where the posts appear

### How to set it up

Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Setup takes three credentials and your channel’s id.

What you need first

| Need | Detail |
| --- | --- |
| n8n | On n8n Cloud or on a server of your own |
| YouTube | A channel you own and a Google OAuth2 credential for the YouTube Data API |
| OpenAI | An API key |
| Discord | A channel with an Incoming Webhook |
| Captions | An English caption track on each video |

1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`.
2. In `YouTube Video Trigger`, replace `<YOUR_YOUTUBE_CHANNEL_ID>` with your channel’s id.
3. Add the YouTube credential and select it in `Retrieve Caption Data` and `Download Captions`.
4. Add an OpenAI credential and select it in `Caption Summary with ChatGPT`.
5. Add a Discord Webhook credential and select it in `Post to Discord`.
6. Click Test workflow, then activate the workflow.

### How to use it

Activate it and publish a video with an English caption track. A minute or so later, check the channel for the post. Try the first video by hand with Test workflow.

What to change for a different result

| To change | Where |
| --- | --- |
| The summary | The prompt in \`Caption Summary with ChatGPT\` |
| The message | The text in \`Post to Discord\` |
| The caption language | The \`en\` in \`Find English Captions\` |
| How often it checks | The poll time in \`YouTube Video Trigger\` |

### Example

A creator uploads a ten-minute tutorial with an English caption track. The feed shows the new video at the next poll.

The workflow downloads the track, and OpenAI sums it up in three bullets. Discord shows the title in bold, the bullets and a Watch link.

### For newcomers and experts

**If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. Here one box watches the feed, two fetch the captions, one reads them as text, one summarizes and one posts. Try it with a short video first.

**For experts.** The feed entry’s id is `yt:video:` followed by the video id, and a regular expression cuts it out. The caption list is a YouTube Data API call, and `Find English Captions` picks a track with a JMESPath expression.

Where to look closer

| Node | What it does | What to know |
| --- | --- | --- |
| \`Retrieve Caption Data\` | Lists the video’s caption tracks | It costs 50 units of quota |
| \`Download Captions\` | Fetches the track | It costs 200 units and needs permission to edit the video |
| \`Caption File Conversion\` | Reads the track as text | The text keeps its time codes |
| \`Caption Summary with ChatGPT\` | Writes three bullets | It names \`gpt-5.6-terra\` |

### Good to know

The workflow works for your own videos only, and a video with no English track stops the run.

- The repair: the summary step named \`gpt-3.5-turbo\`, which OpenAI’s deprecations page, read on 12 November 2026, lists as shut down on 23 October 2026. This copy names \`gpt-5.6-terra\`, the replacement the page gives
- Permission: YouTube’s page on downloading captions says the method requires permission to edit the video
- Quota: each new video costs 250 units of the 10,000 a day
- Tracks: the pages read do not say whether auto-generated tracks can be downloaded, and a new video may have no track yet
- Not run: this copy was not run against YouTube, OpenAI or Discord
- Your data: the captions go to OpenAI, and the title, the summary and the link go to Discord
- Credentials: the JSON holds none

## README

```markdown
# New YouTube videos posted to Discord with AI summaries

An n8n workflow that watches a YouTube channel's feed. For each new video it downloads the English captions, has OpenAI write three bullet points about the video and posts the title, the summary and a link to a Discord channel.

## What is inside

- `workflow.json`: the workflow as n8n exports it, eight nodes: seven that do the work and one sticky note. It holds no credential.
- `README.md`: these notes.

## What we changed from the original copy

- The credential links are gone. Select your own for YouTube, OpenAI and Discord.
- The summary step named `gpt-3.5-turbo`. OpenAI's deprecations page, read on 12 November 2026, lists it as shut down on 23 October 2026, with `gpt-5.6-terra` as the replacement. The step has no tools, and this copy names `gpt-5.6-terra`.
- The feed address named one channel. It now holds `<YOUR_YOUTUBE_CHANNEL_ID>`.
- The sticky note was rewritten. A link to a video tutorial was cut, and lines were added about who may download captions and the need for an English track.
- Nothing else.

## Before you start

- An n8n instance, on n8n Cloud or your own server.
- A YouTube channel that you own, and a Google OAuth2 credential in n8n for the YouTube Data API. The API's page on downloading captions lists the `youtube.force-ssl` scope.
- An OpenAI API key.
- A Discord channel with an Incoming Webhook.
- An English caption track on each video, ready by the time the workflow reads it.

## Set it up

1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`.
2. In `YouTube Video Trigger`, replace `<YOUR_YOUTUBE_CHANNEL_ID>` with your channel's id. YouTube's advanced account settings page shows it.
3. Add the YouTube credential and select it in `Retrieve Caption Data` and `Download Captions`. Sign in with the account that owns the channel.
4. Add an OpenAI credential and select it in `Caption Summary with ChatGPT`.
5. Add a Discord Webhook credential and select it in `Post to Discord`.
6. Click Test workflow, then activate it.

## How a run goes

1. `YouTube Video Trigger` reads the channel's feed every minute and starts a run for each new video.
2. `Retrieve Caption Data` cuts the video id from the feed entry's id, the text after the second colon, and asks YouTube for that video's caption tracks.
3. `Find English Captions` keeps the first track whose language is `en`.
4. `Download Captions` fetches that track.
5. `Caption File Conversion` reads the file as text and stores it under `content`.
6. `Caption Summary with ChatGPT` asks for three bullet points on what the video is about and why to watch it.
7. `Post to Discord` posts the title in bold, the summary and a Watch link.

## Change the look

- The summary: the prompt in `Caption Summary with ChatGPT`.
- The message: the text in `Post to Discord`.
- The caption language: the `en` in `Find English Captions`.
- How often it checks: the poll time in `YouTube Video Trigger`.

## Good to know

- YouTube's page on downloading captions, read on 12 November 2026, says the method "requires the user to have permission to edit the video". The workflow works for your own videos and fails for other people's.
- Each new video costs 250 units of YouTube quota: 50 for the list and 200 for the download. The quota page gives 10,000 units a day.
- The pages read do not say whether auto-generated tracks can be downloaded, and a new video may have no track yet. When no English track is found, `Download Captions` stops with an error.
- YouTube returns the track in its original format, so a file with time codes goes to the model as it is. A long video makes a long prompt.
- This copy was not run against YouTube, OpenAI or Discord.
- The captions go to OpenAI, and the title, the summary and the link go to Discord.
- The JSON holds no credential.
```

## What is in it

3 files, 10 KB, downloaded as a zip.

```text
NOTICE.md  616 B
README.md  4 KB
workflow.json  6 KB
```

## Workflow check

Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run.

- Steps: 7 steps, starting on a Rss Feed Read event
- AI: 1 step calls an AI model: Caption Summary with ChatGPT
- Sign-ins: Signs in to: YouTube, Discord webhook and Rss Feed Read
- API keys: No API key is left in the file
- Step types: Mindket’s checker reads all 6 of its step types

## Get it

- [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/52dd73d6-3a66-4ccd-be61-43448a22f80a)
- [Its page on Mindket](https://mindket.com/p/52dd73d6-3a66-4ccd-be61-43448a22f80a)
