Auto-Generate YouTube SEO Metadata and Thumbnails from Google Drive Videos with n8n

Google Drive video upload → LemonFox transcription → Gemini analysis for title/description/tags/thumbnail → auto-upload to YouTube → permission cleanup

Who

Content creators or ops teams who want to automate YouTube publishing and SEO packaging from raw videos

You get

After a video lands in Drive, the workflow transcribes, generates SEO metadata and a thumbnail, then publishes to YouTube

You need

n8n · google-drive · lemonfox

Steps

1. Configure trigger and temporary access

   After importing the template, configure the Google Drive Trigger node: set event=fileCreated, triggerOn=specificFolder, and enter the folderToWatch to monitor (e.g., a transcript folder). Next, configure the If Video Mime Type node with the condition mimeType contains video so only video files proceed. Then configure Grant Temp File Access using Google Drive OAuth2 credentials to add an anyoneWithLink reader permission so external services can download the video.

2. Transcribe video and clean subtitles

   Configure the Post Audio to Lemonfox node: method POST, URL https://api.lemonfox.ai/v1/audio/transcriptions, authentication HTTP Bearer Auth with your LemonFox API key; body parameters include file pointing to the Drive download link (already referencing the upstream node ID), language=english, and response_format=srt. After running, the Clean SRT Content code node automatically removes escaped quotes and newlines and trims extra blank lines. Then the Create Text File in Drive node writes the cleaned .srt back to Drive for archiving.

   Execution prompt · Source text。JS Code field of the Clean SRT Content node

   Copy prompt

   // Get raw string
   let raw = $json.data;
   
   // Step 1: Remove wrapping quotes if present
   if (raw.startsWith('"') && raw.endsWith('"')) {
     raw = raw.slice(1, -1);
   }
   
   // Step 2: Unescape characters
   raw = raw
     .replace(/\\"/g, '"')   // \" → "
     .replace(/\\n/g, '\n'); // \n → actual newline
   
   // Step 3: Clean extra blank lines (optional but nice)
   raw = raw.replace(/\n{3,}/g, '\n\n').trim();
   
   // Return as clean SRT
   return [
     {
       json: {
         srt: raw
       }
     }
   ];

3. Extract sponsor information

   The Search Drive Files node automatically queries for a file named after the video filename (without extension) plus _sponsors.txt in the same directory. If found, Fetch File Details downloads it via the Google Drive API, and Extract Content from File converts it to text for the downstream AI node. If you do not need sponsor handling, you can skip or leave this branch empty, but the template retains this query by default.

4. Analyze content with AI and generate thumbnail

   The Content Analysis Agent node receives the transcript and sponsor info, then calls the Gemini Chat Model (gemini-3.1-flash-lite-preview) for analysis. It is connected to Parse Structured Output to enforce strict JSON output. Then the Generate Thumbnail Image node uses gemini-2.5-flash-image (Nano Banana) to create a 16:9 thumbnail based on the AI-generated thumbnail_prompt.

   Execution prompt · Source text。Text / System Prompt field of the Content Analysis Agent node

   Copy prompt

   =**You are an expert YouTube Content Strategist and SEO Specialist. Your task is to transform the provided video transcript into a fully optimized YouTube metadata package (Title, Description, Tags, and Hashtags) designed for high CTR and search discoverability.**
   
   ---
   
   **Video Transcript:** `{{ $('Post Audio to Lemonfox').item.json.data }}`
   
   
   
   ---
   
   ### **Instructions:**
   
   1.  **Analyze the Transcript:** Identify the "Big Idea," key takeaways, and the most clickable moment to form the basis of the title and hook.
   2.  **Video Title:** Create a compelling, high-CTR title (under 70 characters). Balance SEO keywords with psychological triggers (curiosity, urgency, or transformation).
   3.  **Video Description:**
       * **The Hook:** A strong opening sentence that summarizes the value.
       * **The Summary:** A concise, engaging breakdown of what the viewer will learn (150–300 words).
       * **Formatting:** Use clean spacing and bullet points for readability.
       * **Call to Action:** Include a prompt for viewers to subscribe or comment on a specific topic from the video.
   4.  **Tags & Hashtags:** * Generate 15–20 relevant SEO tags (comma-separated).
       * Generate 3–5 high-reach hashtags.
   5.  **Thumbnail Prompt:** Create a detailed AI image prompt for a 16:9 YouTube thumbnail. Focus on high contrast, "face-to-camera" emotion (if applicable), and bold text overlay suggestions.
   
   ---
   
   **Sponsors:** `{{ $json.data }}`
   
   ### **Sponsor Handling:**
   
   * Check the "Sponsors" input.
   * **If sponsors exist:** * Include a "Sponsored By" section at the top of the `video_description`.
       * Extract and list their **name** and **email**.
   * **If no sponsors exist:** Return an empty array for the sponsors key.
   * And this sponsors had nothingh to do with the description or title so just extract the sponsor seperately.
   ---
   
   ### **Output Format:**
   
   Return **strictly** a valid JSON object with the following structure:
   
   ```json
   {
     "video_title": "Your optimized YouTube title here",
     "video_description": "Your full SEO description including sponsor mentions...",
     "tags": "tag1, tag2, tag3, tag4...",
     "hashtags": "#hashtag1 #hashtag2 #hashtag3",
     "thumbnail_prompt": "Detailed 16:9 AI image generation prompt here...",
     "sponsors": [
       {
         "sponsor_name": "Sponsor Name",
         "sponsor_email": "[email protected]"
       }
     ]
   }
   ```

5. Upload to YouTube and clean up permissions

   [First-test safety] Before the first test, temporarily disconnect the Upload to YouTube API node or point it at a mock endpoint; validate metadata and thumbnails with a test video/account before enabling real uploads. The Upload to YouTube API node sends a multipart/form-data POST to https://api.upload-post.com/api/upload, including the video download link, AI-generated title and description, platform identifier youtube, and the thumbnail binary data from the previous step. You must replace the placeholder enter-your-api-key in the Authorization header with your upload-post.com API key, and replace enter-your-username in the body with your actual username. After upload completes, the Delete Original File permissions in Drive node immediately removes the anyoneWithLink permission to restore privacy.

You are an n8n workflow setup assistant. The user wants to replicate the template that auto-generates YouTube SEO metadata and thumbnails from Google Drive videos. First confirm the user has: 1) an n8n instance; 2) Google Drive OAuth credentials with folder access; 3) a LemonFox API key; 4) Google Gemini API credentials; 5) upload-post.com API credentials. Then guide them to configure the Trigger, transcription node, AI Agent prompt (style adjustable), thumbnail generation model, and upload credentials. Remind them to replace placeholders like folderToWatch, API keys, and username, and suggest testing with a short video before production use.