HumationHuman + Automation
Back to Catalog

HR & IT helpdesk chatbot with audio transcription

Felipe BragaFelipe Braga
40455 views
2/3/2026
OpenAIVector DatabaseEmailQdrantEmbeddings
Official Page

An intelligent chatbot that assists employees by answering common HR or IT questions, supporting both text and audio messages. This unique feature ensures employees can conveniently ask questions via voice messages, which are transcribed and processed just like text queries.

How It Works

  1. Message Capture: When an employee sends a message to the chatbot in WhatsApp or Telegram (text or audio), the chatbot captures the input.
  2. Audio Transcription: For audio messages, the chatbot transcribes the content into text using an AI-powered transcription service (e.g., Whisper, Google Cloud Speech-to-Text).
  3. Query Processing:
    • The transcribed text (or directly entered text) is sent to an AI service (e.g., OpenAI) to generate embeddings.
    • These embeddings are used to search a vector database (e.g., Supabase or Qdrant) containing the companyโ€™s internal HR and IT documentation.
    • The most relevant data is retrieved and sent back to the AI service to compose a concise and helpful response.
  4. Response Delivery: The chatbot sends the final response back to the employee, whether the input was text or audio.

Set Up Steps

  • Estimated Time: 20โ€“25 minutes
  • Prerequisites:
    1. Create an account with an AI provider (e.g., OpenAI).
    2. Connect WhatsApp or Telegram credentials in n8n.
    3. Set up a transcription service (e.g., Whisper or Google Cloud Speech-to-Text).
    4. Configure a vector database (e.g., Supabase or Qdrant) and add your internal HR and IT documentation.
    5. Import the workflow template into n8n and update environment variables for your credentials.

n8n HR/IT Helpdesk Chatbot with Audio Transcription

This n8n workflow automates an HR/IT helpdesk chatbot, capable of understanding and responding to user queries, including those delivered via audio messages. It leverages AI for natural language processing, audio transcription, and knowledge retrieval from a vector store, providing a comprehensive and intelligent support system.

What it does

This workflow streamlines helpdesk interactions by:

  1. Listening for Telegram Messages: It acts as a Telegram bot, receiving incoming text and audio messages from users.
  2. Handling Audio Transcription: If an audio message is received, it uses OpenAI's Whisper model to transcribe the audio into text.
  3. Processing Text Input: It takes the transcribed text (or direct text messages) and prepares it for AI processing.
  4. Leveraging AI Agent for Responses: An AI agent (powered by OpenAI's Chat Model) processes the user's query, utilizing a Postgres-backed vector store for knowledge retrieval and a Postgres chat memory for conversational context.
  5. Responding to Users: The AI agent's response is then sent back to the user via Telegram.
  6. Knowledge Base Management (Manual Trigger): A separate branch allows for manual execution to load and embed documents into the Postgres vector store, keeping the knowledge base up-to-date. This involves:
    • Extracting text from files.
    • Splitting the text into manageable chunks.
    • Generating embeddings using OpenAI.
    • Storing these embeddings in the Postgres PGVector store.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Telegram Bot Token: A Telegram bot configured with a token for the Telegram Trigger and Telegram nodes.
  • OpenAI API Key: An OpenAI API key configured for the OpenAI and Embeddings OpenAI nodes. This is used for audio transcription (Whisper) and text embeddings.
  • PostgreSQL Database with PGVector Extension: A PostgreSQL database with the pgvector extension installed and configured. This is used for the Postgres Chat Memory and Postgres PGVector Store nodes.
  • Knowledge Base Documents: Files (e.g., PDFs, text files) containing HR/IT helpdesk information to populate the vector store.

Setup/Usage

  1. Import the Workflow: Import the provided JSON into your n8n instance.
  2. Configure Credentials:
    • Telegram: Set up a Telegram credential using your bot token.
    • OpenAI: Set up an OpenAI credential with your API key.
    • PostgreSQL: Set up a PostgreSQL credential pointing to your database with the pgvector extension enabled.
  3. Update Node Parameters:
    • Telegram Trigger: Ensure the "Bot Token" is correctly linked to your Telegram credential.
    • Telegram: Ensure the "Bot Token" is correctly linked to your Telegram credential.
    • OpenAI: Link to your OpenAI credential.
    • Embeddings OpenAI: Link to your OpenAI credential.
    • Postgres Chat Memory: Link to your PostgreSQL credential and configure the table name for chat history.
    • Postgres PGVector Store: Link to your PostgreSQL credential and configure the table name for your vector store.
    • AI Agent: Review the "System Message" and "Tools" to ensure they align with your helpdesk requirements. The "Answer questions with a vector store" tool should be connected to your Postgres PGVector Store.
  4. Populate the Knowledge Base:
    • Connect Files: In the "Manual Trigger" branch, connect your knowledge base documents to the Extract from File node.
    • Execute Manually: Run the "Manual Trigger" branch once (or periodically as your knowledge base updates) to process your documents, generate embeddings, and store them in the Postgres PGVector Store.
  5. Activate the Workflow: Once all credentials and parameters are configured, activate the workflow.
  6. Start Chatting: Send messages (text or audio) to your Telegram bot to interact with the HR/IT helpdesk chatbot.

Related Templates

AI multi-agent executive team for entrepreneurs with Gemini, Perplexity and WhatsApp

This workflow is an AI-powered multi-agent system built for startup founders and small business owners who want to automate decision-making, accountability, research, and communication, all through WhatsApp. The โ€œvirtual executive team,โ€ is designed to help small teams to work smarter. This workflow sends you market analysis, market and sales tips, It can also monitor what your competitors are doing using perplexity (Research agent) and help you stay a head, or make better decisions. And when you feeling stuck with your start-up accountability director is creative enough to break the barrier ๐ŸŽฏ Core Features ๐Ÿง‘โ€๐Ÿ’ผ 1. President (Super Agent) Acts as the main controller that coordinates all sub-agents. Routes messages, assigns tasks, and ensures workflow synchronization between the AI Directors. ๐Ÿ“Š 2. Sales & Marketing Director Uses SerpAPI to search for market opportunities, leads, and trends. Suggests marketing campaigns, keywords, or outreach ideas. Can analyze current engagement metrics to adjust content strategy. ๐Ÿ•ต๏ธโ€โ™€๏ธ 3. Business Research Director Powered by Perplexity AI for competitive and market analysis. Monitors competitor moves, social media engagement, and product changes. Provides concise insights to help the founder adapt and stay ahead. โฐ 4. Accountability Director Keeps the founder and executive team on track. Sends motivational nudges, task reminders, and progress reports. Promotes consistency and discipline โ€” key traits for early-stage success. ๐Ÿ—“๏ธ 5. Executive Secretary Handles scheduling, email drafting, and reminders. Connects with Google Calendar, Gmail, and Sheets through OAuth. Automates follow-ups, meeting summaries, and notifications directly via WhatsApp. ๐Ÿ’ฌ WhatsApp as the Main Interface Interact naturally with your AI team through WhatsApp Business API. All responses, updates, and summaries are delivered to your chat. Ideal for founders who want to manage operations on the go. โš™๏ธ How It Works Trigger: The workflow starts from a WhatsApp Trigger node (via Meta Developer Account). Routing: The President agent analyzes the incoming message and determines which Director should handle it. Processing: Marketing or sales queries go to the Sales & Marketing Director. Research questions are handled by the Business Research Director. Accountability tasks are assigned to the Accountability Director. Scheduling or communication requests are managed by the Secretary. Collaboration: Each sub-agent returns results to the President, who summarizes and sends the reply back via WhatsApp. Memory: Context is maintained between sessions, ensuring personalized and coherent communication. ๐Ÿงฉ Integrations Required Gemini API โ€“ for general intelligence and task reasoning Supabase- for RAG and postgres persistent memory Perplexity API โ€“ for business and competitor analysis SerpAPI โ€“ for market research and opportunity scouting Google OAuth โ€“ to connect Sheets, Calendar, and Gmail WhatsApp Business API โ€“ for message triggers and responses ๐Ÿš€ Benefits Acts like a team of tireless employees available 24/7. Saves time by automating research, reminders, and communication. Enhances accountability and strategy consistency for founders. Keeps operations centralized in a simple WhatsApp interface. ๐Ÿงฐ Setup Steps Create API credentials for: WhatsApp (via Meta Developer Account) Gemini, Perplexity, and SerpAPI Google OAuth (Sheets, Calendar, Gmail) Create a supabase account at supabase Add the credentials in the corresponding n8n nodes. Customize the system prompts for each Director based on your startupโ€™s needs. Activate and start interacting with your virtual executive team on WhatsApp. Use Case You are a small organisation or start-up that can not afford hiring; marketing department, research department and secretar office, then this workflow is for you ๐Ÿ’ก Need Customization? Want to tailor it for your startup or integrate with CRM tools like Notion or HubSpot? You can easily extend the workflow or contact the creator for personalized support. Consider adjusting the system prompt to suite your business

ShadrackBy Shadrack
331

๐ŸŽ“ How to transform unstructured email data into structured format with AI agent

This workflow automates the process of extracting structured, usable information from unstructured email messages across multiple platforms. It connects directly to Gmail, Outlook, and IMAP accounts, retrieves incoming emails, and sends their content to an AI-powered parsing agent built on OpenAI GPT models. The AI agent analyzes each email, identifies relevant details, and returns a clean JSON structure containing key fields: From โ€“ senderโ€™s email address To โ€“ recipientโ€™s email address Subject โ€“ email subject line Summary โ€“ short AI-generated summary of the email body The extracted information is then automatically inserted into an n8n Data Table, creating a structured database of email metadata and summaries ready for indexing, reporting, or integration with other tools. --- Key Benefits โœ… Full Automation: Eliminates manual reading and data entry from incoming emails. โœ… Multi-Source Integration: Handles data from different email providers seamlessly. โœ… AI-Driven Accuracy: Uses advanced language models to interpret complex or unformatted content. โœ… Structured Storage: Creates a standardized, query-ready dataset from previously unstructured text. โœ… Time Efficiency: Processes emails in real time, improving productivity and response speed. *โœ… Scalability: Easily extendable to handle additional sources or extract more data fields. --- How it works This workflow automates the transformation of unstructured email data into a structured, queryable format. It operates through a series of connected steps: Email Triggering: The workflow is initiated by one of three different email triggers (Gmail, Microsoft Outlook, or a generic IMAP account), which constantly monitor for new incoming emails. AI-Powered Parsing & Structuring: When a new email is detected, its raw, unstructured content is passed to a central "Parsing Agent." This agent uses a specified OpenAI language model to intelligently analyze the email text. Data Extraction & Standardization: Following a predefined system prompt, the AI agent extracts key information from the email, such as the sender, recipient, subject, and a generated summary. It then forces the output into a strict JSON structure using a "Structured Output Parser" node, ensuring data consistency. Data Storage: Finally, the clean, structured data (the from, to, subject, and summarize fields) is inserted as a new row into a specified n8n Data Table, creating a searchable and reportable database of email information. --- Set up steps To implement this workflow, follow these configuration steps: Prepare the Data Table: Create a new Data Table within n8n. Define the columns with the following names and string type: From, To, Subject, and Summary. Configure Email Credentials: Set up the credential connections for the email services you wish to use (Gmail OAuth2, Microsoft Outlook OAuth2, and/or IMAP). Ensure the accounts have the necessary permissions to read emails. Configure AI Model Credentials: Set up the OpenAI API credential with a valid API key. The workflow is configured to use the model, but this can be changed in the respective nodes if needed. Connect the Nodes: The workflow canvas is already correctly wired. Visually confirm that the email triggers are connected to the "Parsing Agent," which is connected to the "Insert row" (Data Table) node. Also, ensure the "OpenAI Chat Model" and "Structured Output Parser" are connected to the "Parsing Agent" as its AI model and output parser, respectively. Activate the Workflow: Save the workflow and toggle the "Active" switch to ON. The triggers will begin polling for new emails according to their schedule (e.g., every minute), and the automation will start processing incoming messages. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.

DavideBy Davide
1616

Automated YouTube video uploads with 12h interval scheduling in JST

This workflow automates a batch upload of multiple videos to YouTube, spacing each upload 12 hours apart in Japan Standard Time (UTC+9) and automatically adding them to a playlist. โš™๏ธ Workflow Logic Manual Trigger โ€” Starts the workflow manually. List Video Files โ€” Uses a shell command to find all .mp4 files under the specified directory (/opt/downloads/ๅ•่ฏๅก/A1-A2). Sort and Generate Items โ€” Sorts videos by day number (dayXX) extracted from filenames and assigns a sequential order value. Calculate Publish Schedule (+12h Interval) โ€” Computes the next rounded JST hour plus a configurable buffer (default 30 min). Staggers each videoโ€™s scheduled time by order ร— 12 hours. Converts JST back to UTC for YouTubeโ€™s publishAt field. Split in Batches (1 per video) โ€” Iterates over each video item. Read Video File โ€” Loads the corresponding video from disk. Upload to YouTube (Scheduled) โ€” Uploads the video privately with the computed publishAtUtc. Add to Playlist โ€” Adds the newly uploaded video to the target playlist. ๐Ÿ•’ Highlights Timezone-safe: Pure UTC โ†” JST conversion avoids double-offset errors. Sequential scheduling: Ensures each upload is 12 hours apart to prevent clustering. Customizable: Change SPANHOURS, BUFFERMIN, or directory paths easily. Retry-ready: Each upload and playlist step has retry logic to handle transient errors. ๐Ÿ’ก Typical Use Cases Multi-part educational video series (e.g., A1โ€“A2 English learning). Regular content release cadence without manual scheduling. Automated YouTube publishing pipelines for pre-produced content. --- Author: Zane Category: Automation / YouTube / Scheduler Timezone: JST (UTC+09:00)

ZaneBy Zane
226