anaksor-ocr
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
New
New YouTube videos announced on X with an AI-written post
Newversion 1 · updated
Overview
An n8n workflow that checks your YouTube channel every 30 minutes, has OpenAI write a short post about a video published in that time, and publishes the post on your X account.
New YouTube videos announced on X with an AI-written post is an n8n workflow in the Marketing & SEO category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.
At a glance
- Runs in
- n8n Cloud: import the file into a new workflow there
- Your own n8n server: the same file and steps
- Another model: swap the OpenAI node for any chat model node
Platform
How it works
Trigger
Schedule
It starts by itself every 30 minutes, once the workflow is published, and needs:
- Your YouTube channel ID, set in Fetch Latest Videos
Actions
- YouTube is asked for the newest video on your channel from the last 30 minutes
- The model writes a short post with the video’s link, title and description in mind
- The post is published on your X account
- When no video is found, the run ends without a post
Result
A new post on your X account announcing your latest YouTube video
Integrations
What you need before you start.
YouTube
Video lookup
Finds the newest video on your channel in the last 30 minutes.
NeedsYouTube sign-in and your channel ID
OpenAI
Post writer
Writes the short post and includes the video link.
NeedsOpenAI API key
X
Publisher
Publishes the post on your account.
NeedsX sign-in from a developer app, and API credits
Workflow check
Checked by Mindket on 13 Nov 2026
- Steps
- 4 steps, starting on a schedule
- AI
- 1 step calls an AI model: Write Post for X
- Sign-ins
- Signs in to: YouTube and X
- API keys
- No API key is left in the file
- Step types
- Mindket’s checker reads all 4 of its step types
About
What it is
This n8n workflow announces your new YouTube videos on X. Every half hour it asks YouTube for the newest video on your channel that was published in that time. OpenAI writes a short post with the video’s link, and the workflow publishes that post on your X account. Six nodes make it up, and two of them are notes.
Who it suits
Creators, small channels and marketing teams that want every upload announced on X without writing the post by hand. Skip it if you want to approve each post first, since it publishes as soon as a video is found.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| Media | Video creators | Announce each upload | A creator uploads a video and finds the announcement on X within the half hour. |
| Education | Course channels | Tell followers about a new lesson | A teacher’s channel posts a lesson and X followers get a short note with the link. |
| Business | Marketing teams | Keep a brand account active | A team that uploads product demos gets each one announced without extra work. |
| Software | Developer channels | Share a release video | A developer channel posts a release video and the announcement names its main feature. |
You need a little n8n: import a file, add three credentials and publish the workflow so its schedule runs.
Where to use it
Any n8n that can reach YouTube, OpenAI and X will run it. It starts on its own every half hour once the workflow is published.
- n8n Cloud: import the file into a new workflow there
- Your own n8n server: the same file and steps
- Another model: swap the OpenAI node for any chat model node
Setup
Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. You need your YouTube channel ID and sign-ins for YouTube, OpenAI and X.
| Need | Detail |
|---|---|
| n8n | On n8n Cloud or on a server of your own |
| YouTube | A Google sign-in with the YouTube Data API turned on, and your channel ID |
| OpenAI | An API key |
| X | A sign-in from an X developer app, with API credits to post |
- In n8n, create a workflow, open its menu, choose Import from File and pick
workflow.json. - Add a YouTube credential and select it in
Fetch Latest Videos. - In
Fetch Latest Videos, replace<YOUR_YOUTUBE_CHANNEL_ID>in Channel ID with your own channel ID. - Add an OpenAI credential and select it in
Write Post for X. - Add an X credential and select it in
Post to X. - Publish the workflow so the schedule runs.
How to use it
Leave it published and upload a video. Within half an hour of that upload, a run finds it and posts. Check your X account, and unpublish the workflow when you want the posts to stop.
| To change | Where |
|---|---|
| How often it checks | The interval in Check Every 30 Min |
| The look-back window | The 30 in the date expression in Fetch Latest Videos |
| The style of the post | The message in Write Post for X |
| The model | Write Post for X |
| What gets posted | The text field of Post to X |
Example
A creator publishes a video titled “Ten shortcuts for spreadsheets”. At the next check, Fetch Latest Videos returns it, and the model writes a short post with a link of the form https://youtu.be/<video ID>. Post to X publishes that text on the creator’s account.
If a run finds no recent video, nothing is written or posted.
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. A schedule trigger starts a run at a fixed interval. A credential stores the sign-in that lets n8n act on your behalf.
For experts. Fetch Latest Videos calls YouTube’s search with your channel ID, a publishedAfter time of 30 minutes ago and a limit of 1. Write Post for X reads the video ID, title and description, and Post to X publishes the model’s message.content.
| Node | What it does | What to know |
|---|---|---|
Check Every 30 Min | Starts a run every half hour | Runs only while the workflow is published |
Fetch Latest Videos | Finds the newest video in the window | Returns at most one |
Write Post for X | Writes the post and the link | Told to stay under 140 characters |
Post to X | Publishes the post | Goes live at once |
Good to know
One model line needed a swap, and every post goes live without a check.
- Model:
gpt-3.5-turbowas shut down on 23 October 2026, according to OpenAI’s page read on 12 November 2026, and that page namesgpt-5.6-terra, which Mindket’s copy uses - Live posts: a run that finds a video publishes at once, and nothing asks you first
- Gaps and repeats: the look-back window matches the check interval, so a video near the edge of a window can be missed or posted twice. Only the newest one is posted
- Length: the model is asked for at most 140 characters, but a model can go over what you ask
- YouTube quota: a project gets 100 search calls a day by default, according to Google’s quota page, and this workflow makes 48
- X access: the API charges by use, through credits bought in X’s developer console
- Not run: Mindket read this copy against n8n’s source and did not run it on a live n8n
- Your data: the video’s ID, title and description go to OpenAI, and the post goes to X
- Credentials: the JSON holds none
README and files
New YouTube videos announced on X with an AI-written post
An n8n workflow that announces your new YouTube videos on X. Every half hour it asks YouTube for the newest video on your channel from that time. OpenAI writes a short post with the video's link, and the workflow publishes that post on your X account.
What is inside
workflow.json: the workflow as n8n exports it, 6 nodes. Four run, and two are sticky notes. It holds no credential.README.md: these notes.
What we changed from the original copy
- The model node used
gpt-3.5-turbo. OpenAI's deprecation page, read on 12 November 2026, lists it as shut down on 23 October 2026 and namesgpt-5.6-terra, which the node now uses. The node is renamedWrite Post for X, and its message now ends with a request for the post text only. - The channel ID in
Fetch Latest Videoswas its author's. It is now<YOUR_YOUTUBE_CHANNEL_ID>, and you replace it with your own. - The two sticky notes are reworded. One pointed to a setup video, and Mindket's copy does not link to it.
- The credential links are gone, and the file's name is ours.
- Nothing else. The schedule, the look-back window, the limit of one video and the post step are as the file had them.
Mindket read this copy against n8n's source. It was not run on a live n8n.
Before you start
- An n8n instance, on n8n Cloud or your own server.
- A YouTube credential in n8n, which is a Google sign-in with the YouTube Data API turned on, and your channel ID. YouTube's help page says it is listed under Settings, then Advanced settings.
- An OpenAI API key.
- An X credential in n8n, from an X developer app that may post for your account.
Set it up
- In n8n, create a workflow, open its menu and choose Import from File. Pick
workflow.json. - Add a YouTube credential and select it in
Fetch Latest Videos. - In
Fetch Latest Videos, replace<YOUR_YOUTUBE_CHANNEL_ID>in Channel ID with your own channel ID. - Add an OpenAI credential and select it in
Write Post for X. - Add an X credential and select it in
Post to X. - To test, press Execute Workflow within 30 minutes of publishing a video. Then publish the workflow so the schedule runs.
What happens in a run
Check Every 30 Minstarts a run every 30 minutes while the workflow is published.Fetch Latest Videosasks YouTube for videos on your channel published after the time 30 minutes ago, with a limit of 1. When there is none, the run ends here.Write Post for Xgives the model the video's link, built from its ID, its title and its description, and asks for an engaging post of at most 140 characters.Post to Xpublishes the model's reply as a new post.
What to change
- How often it checks: the interval in
Check Every 30 Min. - The look-back window: the 30 in the date expression in
Fetch Latest Videos. - The style of the post: the message in
Write Post for X. - The model:
Write Post for X. - What gets posted: the text field of
Post to X.
Good to know
- Posts go live at once. A run that finds a video publishes without asking you, so unpublish the workflow to stop it.
- The look-back window matches the check interval. A video near the edge of a window can be missed or posted twice, and only the newest video in a window is posted.
- The model is asked for at most 140 characters, but a model can go over what you ask. Check how your first posts look.
- Google's quota page says a project gets 100 search calls a day by default. The node uses YouTube's search, so this workflow makes 48 a day.
- X's pricing page says its API charges by use, through credits bought in its developer console.
- Data: the video's ID, title and description go to OpenAI, and the post goes to X.
- Cost: one model call per video found, billed by OpenAI.
NOTICE.md 599 B README.md 4 KB workflow.json 4 KB
What’s new
Reviews
More from Mindket
See all from MindketQwen2.5-7B-Instruct-GGUF by Qwen
Qwen · Kit
Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…
New
ACE-Step 1.5 XL SFT
ACE-Step · Kit
Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…
New
Similar in Marketing & SEO
See all in Marketing & SEOHuashu Design
alchaincyf · Skill
Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…
New29.4k
Pixel Art XL
nerijs · Kit
A pixel art style add-on for Stable Diffusion XL that turns text prompts into pixel-style images, with an optional LCM LoRA for faster runs. For game makers, d…
New
Licon MSR for LTX-2.5
LiconStudio · Kit
Keeps characters, clothing, objects and backgrounds consistent in generated video by feeding the model up to five reference images. A LoRA for LTX-2.5 in Comfy…
New