Workflow Templates

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Telegram Voice AI Assistant This n8n template creates a multimodal Telegram bot that dynamically responds to users: Replies with voice** when receiving voice messages (using ElevenLabs TTS) Replies with text** for text-based queries Supports custom AI tools (e.g., crypto APIs, databases, or custom functions) Built with LangChain Agents, it can integrate any external API or data source into conversations. Key Features 🎙️ Smart Response Logic Voice Query? → Voice Reply** Transcribes audio via ElevenLabs STT Processes with AI (Groq/Gemini) Converts text response to natural speech (ElevenLabs TTS) Text Query? → Text Reply** Bypasses TTS/STT for faster responses 🛠️ Extensible AI Tools Add your own tools: Database lookups Weather/stock APIs Custom Python functions RAG (document retrieval) Supports multi-step tool chaining (e.g., "Get BTC price → analyze trends → summarize") 🌐 Language & Context Auto-detects user language (via Telegram’s language_code) Maintains session memory (remembers conversation history) Use Cases Voice-first customer support** Crypto/analytics assistants** (e.g., "What’s Ethereum’s current gas fee?") Multilingual FAQ bots** Educational tutors** (voice-interactive learning) Requirements Telegram Bot Token** ElevenLabs API Key** (For TTS/STT) Groq API Key* or *Google Gemini API Key** Customization Tips Change AI personality*: Modify the *systemMessage in the Voice Assistant node Add more models**: Swap Groq/Gemini for OpenAI, Anthropic, etc. Extend functionality**: Add RAG (Retrieval-Augmented Generation) for document queries Take this template to create a Siri-like AI assistant for Telegram in minutes! 🚀

What It Does This intelligent workflow simplifies the complex task of determining whether a website is legitimate or potentially a scam. By simply submitting a URL through a form, the system initiates a multi-agent evaluation process. Four dedicated AI agents—each powered by GPT-4o and connected to SerpAPI—analyze different dimensions of the website: domain and technical details, search engine signals, product and pricing patterns, and on-site content analysis. Their findings are then passed to a fifth AI agent, the Analyzer, powered by GPT-4o mini, which consolidates the data, scores the site on a scale of 1–10 for scam likelihood, and presents the findings in a clear, structured format for the user. Who It's For This workflow is ideal for anyone who needs to quickly and reliably assess the trustworthiness of a website. Whether you're a consumer double-checking a store before making a purchase, a small business owner validating supplier sites, a cybersecurity analyst conducting threat assessments, or a developer building fraud detection into your platform — this tool offers fast, AI-powered insights without the need for manual research or technical expertise. It's designed for both individuals and teams who value accurate, scalable scam detection. How It Works The process begins with a simple form submission where the user enters the URL of the website they want to investigate. Once submitted, the workflow activates four specialized AI agents—each powered by GPT-4o and connected to SerpAPI—to independently analyze the site from different angles: Agent 1 examines domain age, SSL certificates, and TLD trustworthiness. Agent 2 reviews search engine results, forum mentions, and public scam reports. Agent 3 analyzes product pricing patterns and brand authenticity. Agent 4 assesses on-site content quality, grammar, legitimacy of claims, and presence of business info. Each agent returns its findings, which are then aggregated and passed to a fifth AI agent—the Analyzer. This final agent, powered by GPT-4o mini, evaluates all the input, assigns a scam likelihood score from 1 to 10, and compiles a neatly formatted summary with organized insights and a disclaimer for context. Set UP You will need to obtain an Open AI API key from platform.openai.com/api-keys After you obtain this Open AI API key you will need to connect it to the Open AI Chat Model for all of the Tools agents (Analyzer, Domain & Technical Details, Search Engine Signals, Product & Pricing Patterns, and Content Analysis Tools Agents). You will now need to fund your Open AI account. GPT 4o costs ~$0.01 to run the workflow. Next you will need to create a SerpAPI account at https://serpapi.com/users/sign_up After you create an account you will need to obtain a SerpAPI key. You will then need to use this key to connect to the SerpAPI tool for each of the tools agents (Domain & Technical Details, Search Engine Signals, Product & Pricing Patterns, and Content Analysis Tools Agents) Tip: SerpAPI will allow you to run 100 free searches each month. This workflow uses ~5-15 SerpAPI searches per run. If you would like to utilize the workflow more than that each month, create multiple SerpAPI accounts and have an API key for each account. When you utilize all 100 free searches for an account, switch to the API key for another account within the workflow. Disclaimer This tool is designed to assist in evaluating the potential risk of websites using AI-generated insights. The scam likelihood score and analysis provided are based on publicly available information and should not be considered a definitive or authoritative assessment. This tool does not guarantee the accuracy, safety, or legitimacy of any website. Users should perform their own due diligence and use independent judgment before engaging with any site. N8N, OpenAI, its affiliates, and the creators of this workflow are not responsible for any loss, damages, or consequences arising from the use of this tool or the actions taken based on its results.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. 🎬 Seedance Video Marketing AI Agent Description: This AI-powered marketing automation workflow takes a user prompt, researches trending topics, generates a compelling short-form video prompt, and sends it to the Seedance API via Wavespeed to create a ready-to-use video ad — all from a single Telegram message. Built for marketers, founders, and content creators who want to turn trend-based ideas into visual video content without touching a video editor. For the step-by-step video tutorial guide on how to build this workflow, check out: https://youtu.be/2oZ5NhosKgo 🤖 How It Works: 📲 Telegram Trigger  Kick off the workflow by messaging a short prompt (e.g., “Create a 5-second IG ad for my new perfume”) via Telegram. 📈 Trend Research with Perplexity AI (Sonar Pro)  An AI agent scans the latest 14-day trends and selects the top marketing angle based on the product/niche input. 🧠 Video Prompt Engineer (ChatGPT)  Crafts a concise, visually rich video generation prompt — optimized for Seedance — based on the trend insight and product. 🎥 Video Generation (Wavespeed + Seedance API)  Sends the AI-generated prompt to Seedance via Wavespeed to generate a 5-second short-form video ad. 🔁 Status Loop & Response  The workflow checks if the video is ready. Once complete, it sends the final video output URL back to you in Telegram. 🔧 Tools Used: Telegram Trigger & Response Perplexity AI (Sonar Pro) OpenAI Seedance API (via Wavespeed) n8n HTTP Request, Wait, and Loop nodes 💡 Use Cases: Auto-generate TikTok/Instagram ads from current trends Scale creative content generation with zero design work Plug into your marketing chatbot or campaign assistant Use trends as visual inspiration for ad creatives If you like the build, check out my channel and consider subscribing: https://www.youtube.com/@Automatewithmarc

This workflow offers an effective way to handle a chatbot's functionality, making use of multiple tools for information retrieval, conversation context storage, and message sending. It's a setup tailored for a Slack environment, aiming to offer an interactive, AI-driven chatbot experience. Note that to use this template, you need to be on n8n version 1.19.4 or later.

Template to get your public IP address and push it to Namecheaps Dynamic DNS per subdomain. Open "yourdomain.com" Insert your domain and your Namecheap DDNS password Open "subdomains" Replaces and insert your subdomains Execute Workflow Have fun!

This n8n template demonstrates walks you through a fully automated process to generate faceless videos - from script creation to final download - using AI-generated voice, images, and smart video editing. Use cases are many: This tool is perfect for YouTube and Shorts creators who want to publish daily content without showing their face, TikTok and Reels marketers automating voice-over-driven videos, and solopreneurs scaling up their content without hiring a team. It’s also ideal for agencies producing batches of faceless video ads, automation enthusiasts building smart media workflows in n8n, and anyone who’s rich in ideas but tired of spending hours editing. How It Works Phase 1: Provide Topic Input A short topic and idea should be entered into the Idea part in Node Fields - Set Idea inside the workflow in n8n. Trigger the process manually by clicking Test Workflow or Execute Workflow. Phase 2: Script Generation Your idea is passed to Google Gemini's chat model. The model returns a concise, 60-second faceless video script. The script is then reformatted into a structured layout optimized for voice generation and visual synchronization. Phase 3: Audio Generation The formatted script is passed to ElevenLabs, which turns the text into a high-quality voiceover audio. The generated audio is uploaded to Google Drive and made publicly accessible. At the same time, the audio is sent to OpenAI Whisper via a POST request to generate a transcription of the voiceover. Phase 4: Timestamps Generation The tool merges the original script and the OpenAI Whisper-generated transcription. The merged data is passed to Google Gemini's chat model to generate image prompts with precise timestamps. The output is parsed and cleaned using a structured parser to ensure it's in ready-to-use JSON format for image generation. Phase 5: Images Generation The full list of timestamped prompts is is split into individual entries. Each prompt is sent to Leonardo's API that turns text descriptions into visuals. A delay of 30 seconds is added to give the image generation engine enough time to complete rendering. Once completed, the workflow retrieves all final images for the next stage. Phase 6: Images To Video Conversion All generated images are sent to Leonardo's API, which stitches them together based on the structured prompts and timing. A 5-minute wait allows time for rendering. After the wait, the workflow retrieves the generated small videos and makes them downloadable. Then, the tool aggregates all downloaded videos into a single unified structure, preparing them for the final editing. Phase 7: Video Editing and Downloading The raw video, along with timestamps or subtitles, is sent to Shotstack, a video editing tool that supports advanced edits. A delay of 1 minute allows Shotstack to process the edit. Then, the tool checks whether the edited video is finished by Shotstack and ready to be downloaded. Once completed, you can download the final polished video to your local storage for later use. How To Use Download the workflow package. Import the package into your n8n interface. Set up necessary credentials for tools access and usability: For Google Gemini access, please connect to its API in the following nodes: Node Google Gemini Chat Model 1 Node Google Gemini Chat Model 2 For Google Drive access, please ensure connection in the following nodes: Node Upload Audio to Drive Node Make Audio File Public For ElevenLabs access, please connect to its API in the following node: Node Generate Voice For OpenAI Whisper access, please connect to its API in the following node: Node Transcribe Audio with OpenAI Whisper For Leonardo access, please allow connection to its API in the following nodes: Node Generate Images Node Generate Videos/Scenes For Shortstack access, please connect to its API in the following nodes: Node Edit with Shotstack Node Render Final Video with Shotstack Input your video idea or short description as a string in Node Fields - Set Idea in n8n. Run the workflow by clicking Execute Workflow or Test Workflow. Wait the process to run and finish. View the result in Node Download Final Video and download it in your local storage for later use. Requirements Basic setup in Google Cloud Console (OAuth or API Key method enabled) with enabled access to Google Drive. Google Gemini API** access with permission to use chat-based large language models. ElevenLabs API** access for generating high-quality voiceovers from scripts. OpenAI Whisper API** access to transcribe voiceovers into clean text. Leonardo API** access for both image and video generation tasks. Shotstack API** access for editing and rendering the final video with enhanced visuals and timing. How To Customize You can input your requested video topic or description directly in Node Fields – Set Idea. By default, the script length is set to around 60 seconds in Node 60 Second Script Writer. You can easily change this in the prompt to create shorter or longer videos based on your needs. While the default setup uses Google Gemini for script and prompt generation, you can replace it with OpenAI ChatGPT, Claude, or any other compatible chat-based model you prefer. The voiceover is currently created using ElevenLabs, but you’re free to substitute it with other text-to-speech engines like Google Cloud Text-to-Speech, HeyGen, etc. We're using OpenAI Whisper to transcribe the voiceover into text. You can switch to alternatives such as AssemblyAI, Deepgram, or other compatible providers depending on your preference. This workflow uses Leonardo for both image and video generation. You can swap it out for other compatible providers based on availability or style preference. Video editing is handled by Shotstack by default. You can plug in alternatives like Runway, FFmpeg, or other API-based editors depending on your editing needs or desired effects. If you’d like this workflow customized to fit your tools and platforms availability, or if you’re looking to build a tailored AI Agent for your own business - please feel free to reach out to Agent Circle. We’re always here to support and help you to bring automation ideas to life. Need Help? Join our community on different platforms for support, inspiration and tips from others. Website: https://www.agentcircle.ai/ Etsy: https://www.etsy.com/shop/AgentCircle Gumroad: http://agentcircle.gumroad.com/ Discord Global: https://discord.gg/d8SkCzKwnP FB Page Global: https://www.facebook.com/agentcircle/ FB Group Global: https://www.facebook.com/groups/aiagentcircle/ X: https://x.com/agent_circle YouTube: https://www.youtube.com/@agentcircle LinkedIn: https://www.linkedin.com/company/agentcircle

🔮 Mystic Tarot Bot — AI-Powered iMessage Readings This magical n8n template turns your iMessage inbox into a soulful tarot reading experience powered by Blooio and AI. Users can send in questions or photos of their tarot spreads, and the bot replies like a mystical oracle — interpreting symbols, offering gentle insights, and guiding with poetic warmth. ✨ Ideal for solo reflection, spiritual creators, or client-based guidance services — no tech knowledge needed. 🌟 Use Cases Offer intuitive, emotionally resonant tarot readings via iMessage Support coaching, wellness, and metaphysical businesses with AI-enhanced readings Accept photos of real tarot card spreads or plain text questions Great for automating daily card pulls, client responses, or onboarding into spiritual flows 🧠 Good to Know Built using Blooio’s iMessage API — supports image attachments and conversational replies Includes visual recognition and symbolic interpretation of real tarot card photos Responses generated by OpenAI with a custom “Mystic Tarot Reader” persona Onboards users if they say “Hi” or request a virtual card draw Responds in poetic, spiritually attuned language — no markdown, no tech-speak ⚙️ How it Works Trigger: iMessage webhook via Blooio receives user message or image Check: Bot ignores self-sent messages to prevent loops Detect: If a photo is attached, it’s passed to AI for card recognition Interpret: The AI agent gives a heartfelt, symbolic interpretation Respond: A final, warm tarot reading is sent back through iMessage 📝 How to Use Set Up Blooio: Sign up at https://blooio.com Choose a Dedicated or Enterprise plan (image support required) Copy your API key from Settings → API Keys Paste it into the Send Message HTTP node as a Bearer token Customize the Experience: Adjust the prompt for a different tone or deck style Add journaling prompts, affirmations, or follow-ups Use other workflows to track users, create reading logs, or offer upsells Try It Out: Text your Blooio-connected number with: “Hi” → get onboarding “Draw a card for me” → get a virtual pull A tarot photo + question → get a full, soulful reading ✅ Requirements Blooio Account & API Token (Dedicated plan or higher for images) Optional: Tarot images, user questions, or both 🔧 Customizing This Workflow Add personalized spreads (e.g. past/present/future layouts) Send AI-generated visuals of the pulled cards Route readings into Notion, Airtable, or Google Sheets Expand to WhatsApp, web, or email with Blooio’s multichannel support 🃏 Let the cards speak. Let the messages flow.

This n8n workflow template lets teams easily generate a custom AI chat assistant based on the schema of any Notion database. Simply provide the Notion database URL, and the workflow downloads the schema and creates a tailored AI assistant designed to interact with that specific database structure. Set Up Watch this quick set up video 👇 Key Features Instant Assistant Generation**: Enter a Notion database URL, and the workflow produces an AI assistant configured to the database schema. Advanced Querying**: The assistant performs flexible queries, filtering records by multiple fields (e.g., tags, names). It can also search inside Notion pages to pull relevant content from specific blocks. Schema Awareness**: Understands and interacts with various Notion column types like text, dates, and tags for accurate responses. Reference Links**: Each query returns direct links to the exact Notion pages that inform the assistant’s response, promoting transparency and easy access. Self-Validation**: The workflow has logic to check the generated assistant, and if any errors are detected, it reruns the agent to fix them. Ideal for Product Managers**: Easily access and query product data across Notion databases. Support Teams**: Quickly search through knowledge bases for precise information to enhance support accuracy. Operations Teams**: Streamline access to HR, finance, or logistics data for fast, efficient retrieval. Data Teams**: Automate large dataset queries across multiple properties and records. How It Works This AI assistant leverages two HTTP request tools—one for querying the Notion database and another for retrieving data within individual pages. It’s powered by the Anthropic LLM (or can be swapped for GPT-4) and always provides reference links for added transparency.

💬🗂️🤖 This workflow automates the translation of Google Slides presentations from any languages, while preserving the original formatting and slide structure. It leverages Google APIs, AI translation (Gemini/PaLM), and modular execution for high flexibility and accuracy. DISCLAIMER: texts are split by Google Slides APIs into small blocks, so the translation will not always be contextualized. Key Benefits ⚡ Time-Saving**: Automates a typically manual and error-prone task of translating slides. 🌍 AI-Powered Accuracy**: Uses Google Gemini to provide context-aware translations while respecting defined rules. 🔒 Safe & Non-Destructive**: The original presentation is never modified — a new copy is always created. 🎯 Precision**: Skips irrelevant text (e.g., emails, URLs, names) to avoid mistranslation. 🔁 Modular & Scalable**: Uses subworkflows and batching, ideal for presentations with many slides. 🎨 Layout Preservation**: Keeps the original design and formatting intact. How it Works Initialization: The workflow starts with a manual trigger ("When clicking ‘Execute workflow’"). Set the language to translate (IMPORTANT format ISO-639) It duplicates a specified Google Slides presentation ("Duplicate presentation") to create a new copy for translation, preserving the original. Slide Processing: The workflow retrieves slides from the copied presentation ("Get slides from a presentation") and processes them in batches ("Loop Over Items"). For each slide, text content is extracted ("Extract Text") using a custom JavaScript snippet, which identifies and collects text elements while retaining the slide's objectId. Translation: The extracted texts are passed to a LangChain agent ("Translation expert"), which translates the content from Italian to English. The agent follows strict guidelines (e.g., skipping URLs, brand names, etc.). The translated text is sent to the "Translate Google Slides" node, which replaces the original text in the presentation using the slide's objectId for targeting. Execution Flow: The workflow includes delays ("Wait 10 sec" and "Wait 3 sec") to manage API rate limits and ensure smooth execution. The process repeats for each batch of slides until all content is translated. Set Up Steps Prerequisites: Ensure access to the source Google Slides presentation (specified by fileId in "Duplicate presentation"). Set up Google OAuth2 credentials for Google Drive and Slides (nodes reference credentials like "Google Slides account"). Configure the Google Gemini (PaLM) API credentials for the translation agent. Configuration: Update the fileId in the "Duplicate presentation" node to point to your source presentation. Adjust the translation guidelines in the "Translation expert" node if needed (e.g., language pairs or exclusion rules). Modify batch sizes or wait times (e.g., "Wait 10 sec") based on API constraints. Execution: Run the workflow manually or trigger it via the "Execute Workflow" node from another workflow. Monitor progress in n8n’s execution log, as each slide is processed and translated sequentially. Output: The translated presentation is saved as a new file in Google Drive, with the filename including a timestamp (e.g., NAME_PRESENTATION_{lang}_{timestamp}). Note: The workflow is currently inactive ("active": false); enable it after configuration. Need help customizing? Contact me for consulting and support or add me on Linkedin.

Want to learn the basics of n8n? Our comprehensive quick quickstart tutorial is here to guide you through the basics of n8n, step by step. Designed with beginners in mind, this tutorial provides a hands-on approach to learning n8n's basic functionalities.

🎬 Veo3 Instagram Reel Generator – AI-Powered Ad Creation in Minutes Description: This no-code workflow transforms your creative brief into an engaging Instagram Reel using OpenAI and Veo3 API (via Wavespeed) — fully automated in n8n. Just type a product, theme, or trend via chat, and get a short-form video plus caption delivered and logged, ready to post. Perfect for marketers, creators, and content teams looking to scale their ad content output without hiring editors or creative agencies. Watch step-by-step build video tutorial here: https://www.youtube.com/@Automatewithmarc ⚙️ How It Works: 💬 Chat Trigger  Start by sending a message like “Create an ad for a minimalist perfume brand using the ‘quiet luxury’ trend.” 🧠 Prompt Engineer (ChatGPT)  Generates a 5–8 second descriptive video prompt suitable for Veo3 based on your input — including visual tone, motion, and hook. 📡 API Call to Veo3 via Wavespeed  Submits the prompt to create a short video (9:16 ratio, ~8 seconds), then polls for the final video URL. ✍️ Caption Generator (GPT)  Creates an Instagram-friendly caption to pair with the video, using a playful, impactful writing style. 📄 Google Sheets Integration  Logs each generated video prompt, final video URL, caption, and status into a Google Sheet for easy management and scheduling. 🔌 Tools & Integrations: OpenAI GPT (Prompt generation & caption copywriting) Veo3 via Wavespeed API (Video generation) Google Sheets (Content tracking and publishing queue) Telegram / Chat UI trigger (Optional – easily swappable) 💡 Use Cases: Instagram & TikTok ad generation Creative automation for digital agencies Short-form UGC testing at scale Trend-driven campaign ideation

Overview Do you often forget to record expenses? 你是不是會常常忘記紀錄花費? Let Spending Tracker Bot help you! 讓 Spending Tracker Bot 來幫你! This AI image/text Spending Tracker LINE Bot Workflow allows you to quickly create a customized spending tracker robot without writing a line of code. At any time, you can speak or send a photo, and the AI will parse it and automatically log the expense to your cloud ledger. 這套 AI 圖片文字記帳 LINE Bot Workflow ，讓你不用寫一行程式碼，就能快速打造一個量身訂製的記帳機器人。無論何時，只需要口述或發送一張照片，AI 就會幫你整理好自動計入雲端帳本 Preparation ① Enable the Google Sheets API in GCP and complete the OAuth setup ② Create the Google Sheet and populate the field names (Feel free to modify based on your own needs) ③ Configure the Webhook URL in the LINE Developers Console ④ OpenAI API Key ① 在 GCP 啟用 Google Sheets API，並完成 OAuth ② 建立並填好 Google Sheet 欄名 (按照自己的需求做更動） ③ 於 LINE Developers 控制台設定 Webhook URL ④ OpenAI API Key Node Configurations Webhook Purpose: The URL is used to receive incoming requests from LINE. Configuration: Paste this URL into the Webhook URL field in your LINE Developers Console. 用途: 要接收 Line 的 URL 設定: 將 URL 放到 Line Webhook URL Switch based on Expense Type & Set/Https Purpose: To distinguish whether the incoming message is text or an image. Configuration: Use a Switch node to route the flow accordingly. 用途: 區分 text 或 image 設定: switch 分流 AI Agent Purpose: To extract and organize the required fields. Configuration: Chat Model & Structured Output Parser. 用途: 整理出需要的欄位 設定: Chat Model & Structured Output Parser Create a deduplication field Purpose: To prevent duplicate entries by creating a unique "for_deduplication" field. Configuration: Join multiple field names using hyphens (-) as separators. 用途: 確保不會重複寫入，先創建一個"去重使用"欄位 設定: 用 - 連接多個欄位 Aggregrate & Merge_all Purpose: To prevent duplicate entries in the data table. Configuration: Read the Google sheet, extract the existing "for_deduplication" column into a dedupeList, and compare it against the newly generated "for_deduplication" value from the previous step. 用途: 防止重複寫入資料表 設定：讀取雲端表，將原本的"去重使用欄位"整理成dedupeList，與前一步整理好的"去重使用"欄位做比對 Response Switch Purpose: To route data and send appropriate replies based on the content. Configuration: Use the replyToken to respond after branching logic. Depending on the result, either write to the data table or return a message: ✅ Expense recorded successfully: <for_deduplication> Irrelevant details or images will not be logged. ⚠️ This entry has already been logged and will not be duplicated. 用途: 資料分流，回應訊息 設定：使用 replyToken ，資料分流後，寫入資料表或回應訊息 ✅ 記帳成功 : <去重使用欄位> 不相關明細或圖片，不會計入 ⚠️ 此筆資料已記錄過，不會重複記帳 Step by step teaching notes 【Auto Expense Tracker from LINE Messages with GPT-4 and Google Sheets】 【AI 圖片文字記帳 Line Bot，自動記帳寫入 Google Sheet】