Marketplace
İndirebileceğin 3.557 hazır workflow dosyası, artı 10.661 kaynağa bağlı n8n referansı.
Create real estate listing video ads with OpenAI and Videotok
Quick Overview This workflow takes a real estate listing, uses OpenAI to generate ad copy and a video generation prompt, then sends it to the Videotok API to create a 9:16 vertical listing video ad with a caption and compliance notes. How it works Starts manually to test the workflow with a sample property listing. Builds a listing record containing the address, listing details, and image URLs (replace this with your real listing source). Sends the listing data to OpenAI to generate structured JSON for a video ad, including a script, generation prompt, caption, and compliance notes. Parses the OpenAI output and maps it into a Videotok generation payload with brand kit, reference images, quality, duration, and an idempotency key. Calls the Videotok Generations API to create the vertical video ad using the generated prompt and listing images. Setup Add environment variables for OPENAI_API_KEY, VIDEOTOK_API_KEY, and VIDEOTOK_BRAND_KIT_ID. Replace the sample listing step with your own source (CRM, Airtable, Google Sheets, MLS export, or scraper) and ensure it outputs address, listing_details, and listing_image_urls. Confirm the Videotok template slug (viral-video-ads) and adjust the vi
Analyze LinkedIn profiles and posts with Apify and OpenAI GPT-4
Quick overview This workflow collects a LinkedIn profile URL via an n8n form, scrapes the profile’s recent posts with Apify, analyzes the profile and each post using OpenAI models, and stores the resulting profile summary and per-post insights in n8n Data Tables. How it works Receives a LinkedIn profile URL when a user submits the built-in n8n form. Extracts the LinkedIn username from the URL and runs an Apify actor to scrape the profile’s posts into a dataset. Generates an overall competitive-intelligence style profile analysis from the scraped posts using an OpenAI chat model and parses the result into structured JSON. Saves the structured profile summary, themes, messaging patterns, and content ideas to an n8n Data Table. Loops through each scraped post, stores the raw post text and engagement metrics in an n8n Data Table, and marks it as unprocessed. Analyzes each post with an OpenAI chat model to extract structured insights (topic, takeaway, engagement insight, and suggested use) and updates the corresponding Data Table row as processed. Setup Configure the n8n Form Trigger and share the form URL with users who will submit LinkedIn profile links. Add an Apify API token in n8n
CW
Log Airtable worklogs to Tempo with Jira and Slack notifications
Quick overview This workflow runs nightly to pull time entries from Airtable, converts Jira issue keys to issue IDs, logs the time to Tempo via its REST API, archives the processed entries back to Airtable, and sends a confirmation message to a Slack user. How it works Runs on a schedule. Fetches all records from the Airtable “Daily Worklog” table. Looks up each entry’s Jira issue by Issue Key to retrieve the issue ID. Builds a Tempo worklog payload (authorAccountId, issueId, start date/time, description, and time spent calculated from start/end times). Sends each worklog to the Tempo to create the worklog entry. Archives each submitted entry into the Airtable “Worklog History” table and deletes the original record from “Daily Worklog”. Aggregates the processed records and sends a direct message in Slack confirming the upload. Setup Connect Airtable credentials and update the base ID and table IDs for “Daily Worklog” and “Worklog History” to match your Airtable setup. Connect Jira Software Cloud credentials with access to the projects/issues referenced by the Airtable Issue Key field. Connect an HTTP Bearer credential using your Tempo API token, and replace YOUR_TEMPO_AUTHOR_ID in
WBack up workflows daily to GitHub with incremental updates
Quick overview This workflow runs nightly to back up all workflows from your n8n instance to a GitHub repository, creating a new JSON file for new workflows and only updating existing files when the workflow has changed to avoid unnecessary commits. How it works Runs every day at 11 PM on a schedule trigger. Retrieves a list of all workflows in your n8n instance using the n8n API and processes them one by one. Checks GitHub to see whether a backup JSON file already exists for the current workflow. If no file exists, fetches the full workflow JSON from n8n and creates a new file in the GitHub repository. If a file exists, calls the GitHub Commits API to get the latest commit date for that file and compares it to the workflow’s updatedAt date in n8n. If n8n is newer, downloads the latest workflow JSON and updates the existing file on GitHub; otherwise it skips updating to avoid creating a commit. Waits 10 seconds between GitHub operations to reduce the chance of hitting GitHub API rate limits. Setup Create an n8n API key and add an n8n API credential, then select it in the n8n nodes that list and fetch workflows. Create a GitHub Personal Access Token with repo access and add a GitHub
WSend railway queue predictions with OpenAI GPT-4o-mini, Gmail, and Google Sheets
Quick overview This workflow collects train trip details via an n8n Form, predicts station crowding and queue times with a rule-based algorithm, generates a short advisory with OpenAI, then emails a color-coded HTML alert via Gmail and logs each prediction to Google Sheets. How it works Receives a submission from an n8n Form containing the traveler’s train, station, date/time, class, e-ticket status, passenger count, and email. Calculates a crowd score, alert level, queue-time breakdown (platform, ticket counter, security, walking), and an optimal station arrival time using an in-workflow rules engine. Sends the prediction context to OpenAI Chat Completions (gpt-4o-mini) to generate a plain-text, under-120-word travel advisory. Combines the advisory with the prediction results and assigns alert colors and text based on the computed alert level. Builds a color-coded HTML email summarizing the recommended arrival time and queue breakdown. Appends the prediction details to a Google Sheets tab and sends the HTML alert email to the traveler via Gmail. Setup Add an OpenAI API credential for the HTTP request to https://api.openai.com/v1/chat/completions. Connect Google Sheets OAuth2 and r
WRun a Telegram productivity assistant with OpenRouter, Google Calendar, and Todoist
Quick overview This workflow turns Telegram into a personal assistant that manages your Google Calendar and Todoist, sends daily briefings, and alerts you when meetings are booked or things break. How it works Morning briefing - Every day at a set time, the workflow checks your Google Calendar for today's events and your Todoist for open tasks, then sends you two Telegram messages: a calendar rundown and a task summary grouped by project with priority flags. Cal.com booking alerts - When someone books, reschedules, or cancels a call on Cal.com, or a meeting ends, the workflow catches the webhook and sends you a Telegram notification with the attendee's name, email, meeting title, and time. Talk to your assistant on Telegram - Message the bot with text or a voice note. Voice notes get transcribed automatically. Your message goes to an AI agent that can read, create, update, or delete calendar events, and create, find, update, complete, or delete Todoist tasks, all through natural conversation. The agent replies back in the same chat. Error alerts - If any part of the workflow fails, you get a Telegram message with the failed node, the error, and a link to the execution, so you catch
Sync Salesforce MQL lead journey timelines with Factors.ai
Quick overview This workflow runs on a schedule to fetch new, unsynced Salesforce leads, pulls account journey activity from the Factors.ai API based on the lead’s email domain, and updates the lead in Salesforce with a formatted journey summary and sync/status fields. How it works Runs on a schedule and loads the last successful run timestamp (defaulting to the last 7 days on first run). Retrieves Salesforce leads created since the last run that match the defined criteria (Demo Request conversion type, not converted, and not yet Factors-synced). Processes leads in batches and checks whether each lead has an email address. For leads with an email, extracts the email domain, waits briefly, and calls the Factors.ai account journey endpoint for that domain. Normalizes the Factors.ai response, searches the returned data for a valid email, and proceeds only when a valid email is found. Updates the Salesforce lead with a formatted journey/activity summary and marks the lead as Factors-synced, or writes a status to Salesforce when the lead has no email or no matching email is found. After all items are processed, commits the current run timestamp as the new last run time to avoid missing
Screen candidate CVs with Google Gemini, Google Sheets, and Gmail
Quick overview This workflow collects candidate applications via an n8n form, extracts text from uploaded PDF CVs, compares each CV to a job description stored in Google Sheets using Google Gemini (via OpenRouter), logs screening results back to Google Sheets, and creates a Gmail draft email for HR review. How it works Candidate submits the n8n-hosted form with their details and a PDF CV. Two operations run in parallel: CV text is extracted from the uploaded PDF, and the matching Job Description is fetched from Google Sheets using the role the candidate entered. Gemini Flash evaluates the CV against the JD and returns a structured recommendation: Strong Interview, Interview, Borderline, or Do Not Proceed, along with a score, matched skills, gaps, and a plain-text summary. The full screening record is logged to a Screening Results tab in Google Sheets. A Gmail draft is created for HR to review and send: a shortlist notification for Interview and above, a rejection for Borderline and below. Setup Open the Config node and fill in spreadsheet_id, jd_sheet_gid, results_sheet_gid, and company_name. Create two tabs in your Google Sheet: Job Description (columns: job_id, title, department,
Review stale Notion docs with Gmail alerts, Slack reports, and OpenAI
Quick overview This workflow runs every Friday to scan a Notion documentation database for pages not edited in 90+ days, marks them as “Needs review,” emails owners of critical stale docs via Gmail, and uses OpenAI to generate a prioritized weekly review plan that it posts to a Slack channel. How it works Runs every Friday at 10:00 on a schedule. Retrieves all pages from a selected Notion database and calculates how many days it has been since each page was last edited, along with its title, URL, owner email, and importance. Filters the list to only documentation pages that have been untouched for 90 days or more. Updates each stale page in Notion by setting its Status to “Needs review.” Sends a Gmail email to the page owner when the stale document is marked as Critical and an owner email is present. Aggregates all stale documents and sends them to OpenAI to draft a short, risk-ranked weekly docs review plan. Posts the generated review plan to a specified Slack channel. Setup Connect credentials for Notion, Gmail, OpenAI (Chat Model), and Slack. Select your target Notion database in the Notion “getAll” step and ensure it contains properties for Owner Email, Importance (Critical/Nor
WMatch packing list PDFs to purchase orders with docling-serve and Ollama
Quick overview This workflow checks an SFTP “pending” folder for packing list PDFs, converts them to OCR text with docling-serve, and uses Ollama (Gemma) to extract structured line items and match them to a purchase order, logging results and moving files to completed or error folders. How it works Runs every hour and lists files in the SFTP pending folder. Filters for PDFs, downloads each file from SFTP, and logs a PENDING status to an n8n Data Table. Uploads the PDF to docling-serve for OCR conversion (RapidOCR, English) and stops with an error status if conversion fails. Sends the converted Markdown text to an Ollama Gemma chat model to extract a normalized packing-list JSON (PO number, parties, and line items). Loads the matching purchase order data and cross-references PO vs packing-list SKUs and quantities to determine whether the document matches. If SKU count matches but SKU text differs, uses an Ollama-based healing step to detect likely OCR-misread SKUs, applies the corrections, and re-runs the cross-reference. Writes the final status (COMPLETED or ERROR) to the n8n Data Table and moves the PDF in SFTP into a folder named after the status (for example, completed/ or error
CTrack Amazon best seller ranks in Airtable with ScraperAPI and Slack
Quick overview This workflow runs daily at 8am to read an ASIN watchlist from Airtable, fetch each Amazon product’s Best Sellers Rank via ScraperAPI, store rank history back in Airtable, and post a consolidated Slack alert when a product’s rank change exceeds a configured threshold. How it works Runs every morning at 8am on a schedule. Searches Airtable for active watchlist items and processes them one at a time. Fetches each product’s Amazon data from ScraperAPI using the ASIN. Parses the Best Sellers Rank text into a numeric rank, calculates the change versus the previous saved rank, and flags items that exceed the watchlist threshold. Creates a new rank-history record in Airtable and updates the watchlist item with the latest rank and check time. Searches Airtable for today’s flagged rank-history records, builds a single digest message, and posts it to a Slack channel if any alerts exist. Setup Add Airtable credentials and select the Base/Table for both the watchlist search, the rank-history create step, the watchlist update step, and the “today’s alerts” search. Ensure your Airtable schema includes a Watchlist table with fields like active, asin, label, rank_threshold, last_ran
Generate branded invoice PDFs from webhook orders with PolyDoc and email
Quick overview This workflow receives an order via webhook, validates required fields, calculates invoice totals, renders a branded invoice PDF using a saved PolyDoc template, emails the PDF to the customer, and returns the same PDF in the webhook response. How it works Receives an order payload in a POST request via an n8n webhook. Validates that the order includes at least one line item and a customer email, and returns a 422 JSON error if the payload is incomplete. Calculates line totals, subtotal, tax amount, and grand total, and formats the invoice data (invoice number, dates, currency, and customer details). Uses PolyDoc to populate a saved template with the invoice data and render an A4 PDF. Sends the generated PDF to the customer by email as an attachment. Returns the generated PDF as the webhook response for immediate download. Setup Create a PolyDoc API credential in n8n and replace YOUR_TEMPLATE_ID with your saved invoice template ID from the PolyDoc dashboard. Configure an SMTP credential (or replace the email step with another provider) and set the sender address (for example, update [email protected]). Copy the webhook URL from the webhook trigger and configure your
WTriage and reply to email threads with GPT-5.2, IMAP, Gmail, and ESP suppression
Quick overview Automatically read inbound email replies, use AI to detect intent and sentiment, and send natural in-thread responses. Opt-out requests are confirmed, pushed to your ESP suppression list, and logged. A hands-off reply layer that keeps your sender reputation clean while every conversation gets fast, human-sounding answer. How it works An IMAP trigger watches your inbox and picks up new reply emails as they arrive. A filter keeps only genuine replies, and a code node strips quoted history and signatures, then parses the sender name, email, and threading headers. A code node builds a strict AI prompt with the cleaned message and your trigger-word hints. The OpenAI node classifies intent and sentiment and drafts a reply, returning strict JSON. A code node normalizes the response, enforces a clean email structure, and adds your CTA once. A switch routes on the unsubscribe flag: normal replies go back in-thread through Gmail, opt-outs get a neutral confirmation. Opt-outs are posted to your ESP suppression list, every action is logged to a data table, and Gmail labels are updated to mark the thread handled. Setup (5 steps): Add your IMAP credentials to the email trigger and
Book calendar appointments with availability checks in Google Calendar
Quick overview This workflow is triggered by another n8n workflow to verify a requested appointment slot and, if available, books a 30‑minute event in Google Calendar, returning a booked/unbooked response with formatted date/time details. How it works Receives appointment details (name, phone, service type, preferred date, preferred time) when called by another n8n workflow. Calls a separate “Check Slot Availability” workflow to determine whether the requested slot is available. If the slot is available, builds ISO start/end timestamps for a 30-minute appointment window. Creates the appointment as a Google Calendar event with a summary and description populated from the input details. Returns a success payload with booked: true and formatted preferred date/time, or returns booked: false with an error code when the slot or calendar booking fails. Setup Create or identify a “Check Slot Availability” workflow and update the referenced workflow ID/name so it returns an available boolean. Add a Google Calendar OAuth2 credential and set the target calendar (email/ID) in the Google Calendar event creation step. Ensure the calling workflow passes name, service_type, preferred_date (ISO dat
Serve text-to-speech MP3 over a webhook with Smallest.ai
Quick Overview This workflow exposes a POST webhook that converts incoming text into an MP3 audio stream using Smallest.ai, optionally using a provided custom voice ID, and returns the audio inline in the same HTTP response. How it works Receives a POST request on the /text-to-speech webhook endpoint with a JSON body. Checks whether the request includes a voice field to indicate a custom voice ID. If a custom voice ID is provided, sends the text and voice ID to Smallest.ai to generate an MP3 with that voice. If no voice ID is provided, sends the text to Smallest.ai to synthesize an MP3 using the default voice settings. Returns the generated MP3 as binary data to the caller with Content-Type: audio/mpeg and an inline filename of speech.mp3. Setup Add your Smallest.ai API credentials in both Smallest.ai speech generation steps. Activate the workflow and copy the production webhook URL, then configure your client to POST to /text-to-speech. Send requests with a JSON payload containing text (required) and voice (optional custom voice ID).
Summarize Zoom meeting recordings in Notion with Smallest.ai and Gemini
Quick Overview This workflow receives Zoom recording webhooks, downloads the meeting recording, transcribes it with Smallest.ai, summarizes it with a Google Gemini-powered AI Agent, and saves the summary and action items as a new page in a Notion database. How it works Receives a POST webhook from Zoom and checks whether the event is Zoom’s endpoint URL validation challenge. For URL validation events, computes the Zoom CRC HMAC SHA-256 token and responds with the plain and encrypted tokens to verify the endpoint. For recording events, immediately acknowledges Zoom with a 200 OK response, then extracts the meeting topic, metadata, and an audio recording download URL from the webhook payload. Downloads the recording file from Zoom using the provided download token for authorization. Sends the downloaded audio to Smallest.ai to generate a full transcription. Uses a LangChain AI Agent with Google Gemini to produce a short meeting summary and a list of action items from the transcript. Creates a new page in a Notion database using the meeting topic as the title and the generated summary as the page content. Setup Create and configure a Zoom Event Notifications webhook (for a recording-c
Transcribe audio to text via webhook with Smallest.ai speech-to-text
Quick Overview This workflow exposes a POST webhook endpoint that accepts a binary audio file, transcribes it to text using Smallest.ai speech-to-text, and returns the transcript in the same synchronous HTTP response. How it works Receives an HTTP POST request on the /transcribe-audio webhook endpoint containing an audio file as binary data. Sends the incoming binary audio (from the audio property) to Smallest.ai for speech-to-text transcription. Extracts the returned transcription and formats it into a transcript field. Responds to the original webhook request with the transcript payload. Setup Create and connect your Smallest.ai API credentials in the Smallest.ai transcription step. Activate the workflow to generate the production webhook URL and use it in your client application. Ensure your client sends the audio file as binary under the audio property when calling the webhook.
Reply to Telegram voice messages with Smallest.ai and Google Gemini
Quick Overview This workflow listens for Telegram bot messages, detects voice audio, downloads the audio file, transcribes it with Smallest.ai, and uses a Google Gemini–powered AI agent to draft a helpful reply that is sent back to the same Telegram chat. How it works Triggers when a new message is received by your Telegram bot. Checks whether the incoming message contains a voice/audio attachment. Downloads the audio file from Telegram using the message’s file ID. Sends the audio to Smallest.ai Speech-to-Text to generate a transcription. Passes the transcription and chat ID to a LangChain AI agent backed by Google Gemini to generate a suggested reply. Sends the formatted response back to the originating Telegram chat. Setup Create a Telegram bot with BotFather, then add your Telegram credentials/token to the Telegram Trigger, file download, and Telegram reply tool nodes. Add your Smallest.ai API credentials to the transcription step. Add your Google Gemini (Google AI) credentials to the chat model used by the AI agent. Start the workflow and message your Telegram bot with a voice note to test the end-to-end transcription and reply.
WAnswer legal questions with Groq using CanLII and CourtListener
Quick overview This workflow collects a legal question via an n8n form, retrieves supporting authorities from CourtListener or CanLII, and uses a Groq-hosted Llama model to produce an answer grounded only in the retrieved text with verified, non-hallucinated citations. How it works Receives a legal question through an n8n form and captures the selected source database (CourtListener or CanLII) plus optional CanLII database and case IDs. Routes the request to CourtListener full-text search or to CanLII case metadata and citator endpoints based on the selected database. For CourtListener, pulls the top search results and fetches the full text of the top-ranked opinion; for CanLII, loads the selected case and a list of related cases from the CanLII citator. Normalizes the retrieved items into a single numbered “sources” block with excerpts that the model can cite. Sends the question and sources to a Groq Chat Model (Llama 3.3 70B) and parses the response into a structured format containing an answer, a supported flag, and a list of citations. Verifies every cited source index against the retrieved sources, drops any mismatches, and renders an HTML result page showing the answer, verif
Draft grounded Gmail support replies from a Notion KB with Groq and Cohere
Quick Overview This workflow ingests published Notion knowledge base articles into an in-memory vector store using Cohere embeddings, then monitors a support Gmail inbox and uses Groq to draft grounded reply emails based only on retrieved KB sources, saving the result as a Gmail draft for review. How it works Manually runs an ingestion flow that pulls all pages from a Notion database and keeps only articles marked as Published. Fetches each article’s Notion page blocks, assembles them into a single document, splits the text into chunks, and embeds the chunks with Cohere. Clears and loads the resulting embeddings and metadata into an in-memory vector store for retrieval. Triggers when an unread Gmail message arrives matching the support inbox query and normalizes the subject, body, sender, and thread details. Uses Groq to classify the email as a support question, noise, or already resolved, and continues only for real support questions. Embeds the question with Cohere, retrieves and reranks the most relevant KB chunks, and stops if the best match does not meet the configured relevance threshold. Uses Groq to draft a reply using only the retrieved sources and, if an answer is produce
File Google Drive inbox documents into dated folders with a Google Sheets audit log
Quick overview This workflow monitors a Google Drive inbox folder for new files, classifies them by filename regex rules, files them into a Year/Month/Type folder structure in Google Drive, and logs each success or failure to a Google Sheets audit log. How it works Triggers every minute when a new file is created in a selected Google Drive folder. Evaluates the filename against configurable regular-expression rules to assign a document type, derive the year/month from the file’s created time, and build a destination path. Uses the planned destination root to find or create the required year folder, then the month folder, then the type folder in Google Drive. Moves the file into the final type folder. Appends a “Filed” audit row to Google Sheets with timestamp, original filename, matched rule, destination path, and file ID. If any step errors, appends a “Failed” audit row to Google Sheets with error details so the run continues. Setup Add Google Drive OAuth2 credentials, select the inbox folder to watch, and ensure the archive root is a different Google Drive folder to avoid reprocessing filed files. In the rules script, paste your archive root folder ID and adjust the filename rege
Back up all workflows to GitHub with daily schedule and Telegram /backup
Quick overview This workflow backs up all workflows from your n8n instance to a GitHub repository every day at 03:00, and also supports an on-demand Telegram /backup command, then sends a Telegram message with the backup result and commit link. How it works Runs daily at 03:00 and also triggers when a Telegram message is received. Checks that the incoming Telegram message starts with /backup before proceeding with the manual run. Fetches all workflows from the n8n instance via the n8n API. Builds a JSON backup file containing the workflows and sets the GitHub file path as backups/YYYY-MM-DD/workflows.json. Checks in GitHub whether the backup file already exists and either updates it or creates it with a dated commit message. Sends a Telegram notification to the triggering chat (or a predefined admin chat for scheduled runs) including the workflow count and GitHub commit URL. Setup Create and select an n8n API credential that can read workflows from your n8n instance. Add a GitHub credential with access to the target repository and set the owner/repo values to your backup repo. Add a Telegram bot credential, enable the Telegram trigger webhook, and use the bot to send /backup from t
Triage PubMed clinical literature with Gemini and Google Sheets and Docs
Quick overview Automatically retrieve recent PubMed articles, identify the three papers most worth reading first using AI, and generate structured clinical literature triage reports in Google Sheets and Google Docs. How it works Reads the first pending literature request from the Google Sheets "Search Requests" tab. Marks the request as “processing” in Google Sheets and builds the PubMed query parameters (keyword, max results, specialty, clinical question, and output language). Searches PubMed via the NCBI E-utilities API (esearch) and fetches the corresponding article abstracts and metadata as XML (efetch). Parses and normalizes the XML into a structured list of candidate articles including title, abstract, journal, publication year, DOI, and PubMed URL. Sends the aggregated candidate articles to Google Gemini to select and rank the best three papers and generate a structured clinical evaluation for each. Appends the three ranked papers with summaries and triage fields to a Google Sheets “Triage Results” tab. Generates a formatted triage report in Google Docs and updates the original request status to “completed” in Google Sheets. Setup Create a Google Sheets OAuth connection and
WGenerate sales call proposals with GPT-4o, Google Slides, PandaDoc, and Gmail
Quick overview This workflow captures details via an n8n form, uses OpenAI to generate structured proposal copy, and then produces a client-ready proposal either by filling a Google Slides template or by creating a PandaDoc document with pricing, before emailing the proposal to the prospect via Gmail. How it works Triggers when a sales rep submits the built-in n8n “Sales Call Logging Form” with the prospect and deal details. Sends the submitted company, problem, solution, scope, timeline, and cost to OpenAI (GPT‑4o) to generate proposal fields as a single JSON object. For the PandaDoc path, creates a PandaDoc document from a template via the PandaDoc API and injects the OpenAI-generated text plus a pricing table based on the form’s Cost value. Emails the PandaDoc proposal to the prospect using Gmail. For the Google Slides path, copies a proposal template in Google Drive and names it using the OpenAI-generated proposal title. Replaces placeholder tokens in the copied Google Slides presentation with the OpenAI-generated proposal sections. Emails the Google Slides proposal link to the prospect using Gmail. Setup Add an OpenAI API credential and confirm the selected GPT‑4o model is ava