--- title: "YouTube short and long script writer with web research" kind: "Kit" category: "Marketing & SEO" price: "Free" seller: "Mindket" version: "2" url: "https://mindket.com/p/6b01afd9-2cbb-4181-b107-49f52a8bf4da" updated: "2026-11-09" --- # YouTube short and long script writer with web research > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that writes a YouTube script from a topic. Tavily searches the web and OpenAI summarizes the pages, with an outline step for long videos. An agent then writes a Short or a long script into a new Google Doc. YouTube short and long script writer with web research is an n8n workflow in the Marketing \& SEO category, listed by Mindket. It is free. This is version 2, last updated on 2026-11-09. 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 writes a YouTube script from a topic. A form takes the topic and a choice between a Short and a long video. Tavily searches the web, OpenAI condenses what the pages say, and an agent writes the script. A Short gets a quick pass: three pages, one summary, one script. A long video gets ten pages, a summary of about 1,000 words and an outline before the script. Either way the script lands in a new Google Doc. A form takes a topic and a Short or long choice → Tavily searches the web for the topic → OpenAI summarizes the pages, and outlines a long video → An agent writes the script in your sample style → Google Docs saves it as a new document ### Who it suits Creators who script their own videos, and the writers and agencies who script for others. It gives you a researched first draft to edit. Skip it if a script must be right on every fact, since its research is only the top pages one search returns. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Creators and solo channels | YouTubers who write their own scripts | Send each topic through the form and edit the draft that appears in Drive | A creator sends a topic on Monday and edits the long script that evening. | | Agencies and freelancers | Scriptwriters for client channels | Keep one set of sample scripts per client and swap them before each run | A freelancer pastes a client’s past scripts into the style nodes so drafts match the channel. | | Tech and product reviews | Channels that make list videos | Ask for a long script on a roundup and let the outline set the order | A review channel asks for a roundup, and each tool gets its own section. | | Education | Course makers and tutors | Turn a how-to topic into a step-by-step script with demonstration cues | A tutor asks for a how-to script, and its steps follow the outline’s order. | | Short-form video | Teams that post Shorts | Pick Short video for fast scripts with a hook and short lines | A social team gets a Short script for each trending topic. | ### Where to use it Any n8n that can reach Tavily, OpenAI and Google will run it. The scripts end up in a Drive folder, where a team can comment on them. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Google Drive: a folder of your choice holds every new document - A team: share the form’s address so writers can request their own scripts ### How to set it up Get it saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Its author puts setup at about 13 minutes. Mindket replaced the two sets of sample scripts: in the original copy, each node held about 33,000 characters of its author’s own channel scripts. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | OpenAI | An API key, for four AI nodes | | Tavily | An API key, held in an HTTP Header Auth credential | | Google | An account that can create documents, for a Google Docs OAuth2 credential, and the ID of a Drive folder | | Your own scripts | A few finished scripts from your channel, short and long, to set the style | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. Add an HTTP Header Auth credential with the name `Authorization` and the value `Bearer`, a space and your Tavily key. Select it in `Tavily` and `Tavily1`. 3. In those two nodes, replace `` in the Authorization header too, so both agree. The brackets go as well. 4. Add an OpenAI credential and select it in `gpt-4o-mini`, `gpt-4o-mini1`, `WebSearch Summary` and `WebSearch Summary (Short)`. 5. Add a Google Docs OAuth2 credential and select it in `Create Doc`, `Update Doc`, `Create Doc1` and `Update Doc1`. 6. In `Create Doc` and `Create Doc1`, replace `YOUR_FOLDER_ID` with your folder’s ID, the part of its address after `/folders/`. 7. In `Reference Script`, replace the placeholder with one or two of your Shorts scripts. In `Reference Script1`, put a long script. 8. Save, send the form once from its test address, then press Publish. ### How to use it Open the form from `On form submission`, type the topic in `Provide topic` and choose Short video or Long video. Both fields are required. The form confirms at once. The research and writing go on behind it, and the document shows up in your folder when the last node finishes. The two paths | Choice | Research | Output | | --- | --- | --- | | Short video | \`Tavily\`: basic depth, 3 results. One summary, then \`AI Agent\` writes the script | A document named after the topic with \`\_Shorts\` added | | Long video | \`Tavily1\`: advanced depth, 10 results. A summary of about 1,000 words, an outline, then \`AI Agent1\` writes a script of 2,500 to 3,000 words | A document named after the topic | What to change for a different result | To change | Where | | --- | --- | | Style | The text in \`Reference Script\` and \`Reference Script1\` | | How much is read | \`max\_results\` and \`search\_depth\` in the \`jsonBody\` of \`Tavily\` and \`Tavily1\` | | Script length and structure | The text of \`AI Agent1\` for long scripts and the system message of \`AI Agent\` for Shorts | | Summary and outline | The messages in \`WebSearch Summary\`, \`WebSearch Summary (Short)\` and \`Create Outline\` | | Document folder | \`folderId\` in \`Create Doc\` and \`Create Doc1\` | ### Example You type `best free video editors for beginners` and choose Long video. Tavily returns ten pages, OpenAI condenses them, and the outline lists each editor with its sub-points. The script follows that order and opens with a short hook. A Doc with the topic as its title appears in your folder. Choosing Short video instead gives a shorter script in a Doc titled `best free video editors for beginners_Shorts`. ### 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. This file has 19, but two are sticky notes that label the Short and long stretches. A credential is a key n8n stores for you and hands to the node you select it in. The style samples matter. The agent copies their tone and pacing. **For experts.** Two OpenAI models share the work across four nodes, and the labels on the model nodes do not match what they run. The model behind each step | Step | Model | What to know | | --- | --- | --- | | \`WebSearch Summary (Short)\` and \`WebSearch Summary\` | chatgpt-4o-latest | OpenAI’s moving alias. The long summary is told to write short sentences at a grade 6 to 8 reading level | | \`Create Outline\` and \`AI Agent1\`, through the node \`gpt-4o-mini\` | chatgpt-4o-latest | The node’s label says mini, its model field says otherwise | | \`AI Agent\`, through the node \`gpt-4o-mini1\` | gpt-4o-mini | The Short script, as plain text with a blank line between beats | The prompts expect a listicle, a how-to or an experiment, but the form sends only Short or Long. The agent has to work the type out from the topic and the outline. ### Good to know Every run searches and calls the model several times, and the long path costs most. - Billing: Tavily and OpenAI each bill their part of a run, and the long path sends up to ten pages of raw text to the model, which can be long - Open form: once the workflow is published, anyone with the form’s address can start a run on your keys - Check the facts: the script is the model’s reading of a few pages, so verify figures and names before you record - The alias: chatgpt-4o-latest may be retired by OpenAI, so pick a current model in those nodes if a run fails there - The notes: the original copy’s agent nodes carried a note naming its author’s channel. Mindket removed both - Credentials: the JSON holds none, and nothing from its author’s accounts ## README ```markdown # YouTube short and long script writer with web research An n8n workflow. Send a topic and a choice of Short or long video through its form. It researches the topic on the web, writes a script and saves it as a new Google Doc. ## What is inside - `workflow.json`: the workflow as n8n exports it, 19 nodes. Two of them are sticky notes that label the Short and long stretches. It holds no credential and no folder ID of its author's. - Two changes to the original copy. Each of the two `Reference Script` nodes held about 33,000 characters of its author's own channel scripts, with a presenter's name. Mindket replaced them with a placeholder for you to fill. The notes on the two agent nodes named its author's channel, and Mindket removed them. - `README.md`: these notes. ## Before you start - An n8n instance, on n8n Cloud or your own server. - An OpenAI API key. - A Tavily API key. - A Google account that can create documents, and a Drive folder for them. - A few finished scripts from your own channel, to set the style. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Add an HTTP Header Auth credential. Give it the name `Authorization` and the value `Bearer`, a space and your Tavily key. Select it in `Tavily` and `Tavily1`. 3. Both of those nodes also carry their own Authorization header, with `Bearer `. Replace the placeholder, brackets included, with your key so the two agree. 4. Add an OpenAI credential. Select it in `gpt-4o-mini`, `gpt-4o-mini1`, `WebSearch Summary` and `WebSearch Summary (Short)`. 5. Add a Google Docs OAuth2 credential. Select it in `Create Doc`, `Update Doc`, `Create Doc1` and `Update Doc1`. 6. In `Create Doc` and `Create Doc1`, replace `YOUR_FOLDER_ID` with the ID of your Drive folder: the part of its address after `/folders/`. 7. Open `Reference Script` and replace its placeholder with one or two of your Shorts scripts. Do the same in `Reference Script1` with a long script. 8. Save, send the form once from its test address, then press Publish at the top of the canvas (or Shift+P). ## The two paths | Choice | Research | Document | |---|---|---| | Short video | `Tavily`: basic depth, 3 results, one summary, then `AI Agent` writes the script | named after the topic, with `_Shorts` added | | Long video | `Tavily1`: advanced depth, 10 results, a summary of about 1,000 words, an outline from `Create Outline`, then `AI Agent1` writes a script of 2,500 to 3,000 words | named after the topic | ## Change the look - Style: the text in `Reference Script` and `Reference Script1`. The agents copy its tone, pacing and layout. - How much is read: `max_results` and `search_depth` in the `jsonBody` of the two Tavily nodes. - Script structure and length: the text of `AI Agent1`, and the system message of `AI Agent` for Shorts. - Summaries and outline: the messages in `WebSearch Summary (Short)`, `WebSearch Summary` and `Create Outline`. ## Good to know - The labels on the model nodes do not match their models. `gpt-4o-mini` runs chatgpt-4o-latest, for the outline and the long script. `gpt-4o-mini1` runs gpt-4o-mini, for the Short script. Both summary nodes run chatgpt-4o-latest. OpenAI may retire that alias, so pick a current model in those nodes if a run fails there. - The prompts expect a listicle, a how-to or an experiment, but the form sends only Short or Long. The agent has to work the type out from the topic and the outline. - The long path sends up to ten pages of raw text to the model, which can be long. Lower `max_results` in `Tavily1` if a run fails on length. - Once the workflow is published, anyone with the form's address can start a run on your Tavily and OpenAI keys. - The script is the model's reading of a few pages. Check figures and names before you record. ``` ## What is in it 2 files, 24 KB, downloaded as a zip. ```text README.md 4 KB workflow.json 20 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 15 steps, starting on a form - AI: 5 steps call an AI model: WebSearch Summary (Short), AI Agent, WebSearch Summary, Create Outline and AI Agent1 - Sign-ins: Signs in to: Tavily, Google Docs and OpenAI - API keys: No API key is left in the file; 1 blank in it for your own key - Step types: Mindket’s checker reads all 8 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/6b01afd9-2cbb-4181-b107-49f52a8bf4da) - [Its page on Mindket](https://mindket.com/p/6b01afd9-2cbb-4181-b107-49f52a8bf4da)