Multimodal Slack AI assistant with voice, image & video processing
What it's for:
This is a base template for anyone trying to develop a Slack bot AI Agent. This base allows for multiple inputs (Voice, Picture, Video, and Text inputs) to be processed by an AI model of their choosing to a get a User started. From here, the User may connect any tools that they see fit to the AI Agent for their n8n workflows.
NOTE: This build is specifically for integrating a Slack bot into a CHAT Channel
If you want to allow the Slack bot to be integrated into the whole workspace, you'll need to adjust some of the nodes and bot parameters
How it works:
Input: Slack message mentioning a bot in a chat channel
n8n Processing: Switch node determines the type:
- Voice Message
- Picture Message
- Video Message
- Text Message
(Currently uses OpenAI and Gemini to analyze Voice/Photo/Video content but feel free to change these nodes with other models)
AI Agent Proccessing: LLM of your choosing examines message and based on system prompt, generates an output
Output: AI Output is sent back in Slack Message
How to use:
1. Create your Slack bot and generate access token
This part will be longest part of the guide but feel free to Youtube search "How to install Slack AI agent" or soemthing similar in case it's hard to follow
- Sign in to the Slack website then go to: https://api.slack.com/apps/
- Click "Create App" (Top Right Corner)
- Choose "From Scratch"
- Enter desired name of App (bot) and desired workspace
- Go to "OAuth and Permissions" tab on the left side of the webpage
- Scroll to "Bot Token Scopes" and Add Permissions: - app_metions:read - channels:history - channels:join - channels:read - chat:write - files:read - links:read - links:write (Feel free to add other permissions here. These are just the ones that will be needed for the automation to work)
- Next, go to "Event Subscriptions" and paste your n8n webhook URL (Find webhook URL by clicking on the Slack trigger node and there should be a dropdown for webhook URL at the very top)
- Go back to "OAuth & Permissions" Tab and install your bot to the Slack workspace (should be a green button under the "Bot User OAuth Token" (Remember where this token is for later because you'll need it to create the n8n credentials)
- Add the bot to your channel by going to your channel, then type "@[your bot name]"
- Should be a message from Slack to add bot to Channel
- Congrats for following along, you've added the bot to your channel!
2. Create Credentials in n8n
- Open Slack trigger node
- Click create credential
- Paste access token (If you followed the steps above, it'll be under "OAuth & Permissions" -> Copy the "Bot User OAuth Token" and paste it in n8n accesss
- Save
3. Add Bot Token to HTTP Request nodes
- Open HTTP Request Nodes (Nodes under the "Downlaod" Note - Scroll down and paste your Bot Access token under "Header Parameters". Should be a placeholder "[Your bot access token goes here]".
- NOTE: Replace everything, including the square brackets
- Do not remove "Bearer". Only replace the placeholder. Finalized Authorization value should be: "Bearer + [Your bot access token]" NOT "[Your bot access token ONLY]"
4. Change ALL Slack nodes to your Slack Workspace and Channel
- Open the nodes, change workspace to your workspace
- Change channel to your channel
- Do this for all nodes
5. Create LLM access token
(Different per LLM but search your LLM + API in google)
- (You will have to create an account with the LLM platform)
- Buy credits to use LLM API
- Generate Access token
- Paste token in LLM node
- Choose your model
Requirements:
- Slack Bot Access Token
- Google Gemini Access Token (For Picture and Video messages)
- OpenAI Access Token (For Voice messages)
- LLM Access Token (Your preference for the AI Agent)
Customizing this workflow:
- To personalize the AI Output, adjust the system prompt (give context or directions on the AI's role)
- Add tools to the AI agent to give it more utility besides a personalied LLM (Example: Calendars, Databases, etc).
Multimodal Slack AI Assistant with Voice, Image, and Video Processing
This n8n workflow creates a powerful AI assistant within Slack, capable of processing various types of media (text, voice, image, video) using advanced AI models and responding directly in the channel. It leverages LangChain agents for intelligent decision-making and integrates with OpenAI and Google Gemini for multimodal capabilities.
What it does
- Listens for Slack Messages: Triggers when a new message is posted in a configured Slack channel.
- Extracts Message Content: Captures the message text, any attached files (images, audio, video), and the user who sent it.
- Determines AI Model: Uses a
Switchnode to intelligently route the message to either an OpenAI or Google Gemini AI agent based on predefined conditions (which can be customized, e.g., based on message content or attachments). - Processes Multimodal Input:
- Text: Directly feeds the text to the chosen AI agent.
- Voice (Audio): Sends audio files to OpenAI for transcription.
- Image: Sends image files to the chosen AI agent for analysis.
- Video: Sends video files to Google Gemini for processing.
- Maintains Conversation Context: Utilizes a
Simple Memorynode to keep track of previous interactions, enabling a more coherent and contextual conversation with the AI. - Generates AI Response: The selected AI agent (OpenAI or Google Gemini) processes the input, potentially using various tools (not explicitly defined in this JSON but implied by the
AI Agentnode), and generates a relevant response. - Posts Response to Slack: Sends the AI-generated reply back to the original Slack channel.
Prerequisites/Requirements
To use this workflow, you will need:
- n8n Instance: A running n8n instance.
- Slack Account & App: A Slack workspace and a Slack App configured with appropriate permissions (e.g.,
channels:history,chat:write,files:read,messages:read). You'll need a Slack API Token and a Signing Secret. - OpenAI API Key: For using the OpenAI language model and audio transcription.
- Google Gemini API Key: For using the Google Gemini language model, especially for video processing.
- Credentials in n8n: Configure credentials for Slack, OpenAI, and Google Gemini within your n8n instance.
Setup/Usage
- Import the Workflow: Download the JSON provided and import it into your n8n instance.
- Configure Slack Trigger:
- Select your Slack credential.
- Choose the Slack channel(s) where the AI assistant should listen for messages.
- Ensure the Slack app is installed in your workspace and has the necessary permissions.
- Configure AI Credentials:
- For the
OpenAInode, select your OpenAI API credential. - For the
Google Gemininode, select your Google Gemini API credential.
- For the
- Customize AI Agents:
- Review the
AI Agentnodes for both OpenAI and Google Gemini. You might want to adjust their prompts, tools, or other parameters to tailor their behavior to your specific needs. - The
Simple Memorynode can be configured for the desired conversation window size.
- Review the
- Configure the Switch Node: The
Switchnode (Node112) currently routes traffic. You will need to define the conditions for routing messages to either OpenAI or Google Gemini based on your requirements (e.g., if message contains video, route to Gemini; otherwise, route to OpenAI). - Activate the Workflow: Once configured, activate the workflow.
The AI assistant will now be active in your designated Slack channel, ready to process multimodal queries.
Related Templates
Auto-create TikTok videos with VEED.io AI avatars, ElevenLabs & GPT-4
π₯ Viral TikTok Video Machine: Auto-Create Videos with Your AI Avatar --- π― Who is this for? This workflow is for content creators, marketers, and agencies who want to use Veed.ioβs AI avatar technology to produce short, engaging TikTok videos automatically. Itβs ideal for creators who want to appear on camera without recording themselves, and for teams managing multiple brands who need to generate videos at scale. --- βοΈ What problem this workflow solves Manually creating videos for TikTok can take hours β finding trends, writing scripts, recording, and editing. By combining Veed.io, ElevenLabs, and GPT-4, this workflow transforms a simple Telegram input into a ready-to-post TikTok video featuring your AI avatar powered by Veed.io β speaking naturally with your cloned voice. --- π What this workflow does This automation links Veed.ioβs video-generation API with multiple AI tools: Analyzes TikTok trends via Perplexity AI Writes a 10-second viral script using GPT-4 Generates your voiceover via ElevenLabs Uses Veed.io (Fabric 1.0 via FAL.ai) to animate your avatar and sync the lips to the voice Creates an engaging caption + hashtags for TikTok virality Publishes the video automatically via Blotato TikTok API Logs all results to Google Sheets for tracking --- π§© Setup Telegram Bot Create your bot via @BotFather Configure it as the trigger for sending your photo and theme Connect Veed.io Create an account on Veed.io Get your FAL.ai API key (Veed Fabric 1.0 model) Use HTTPS image/audio URLs compatible with Veed Fabric Other APIs Add Perplexity, ElevenLabs, and Blotato TikTok keys Connect your Google Sheet for logging results --- π οΈ How to customize this workflow Change your Avatar: Upload a new image through Telegram, and Veed.io will generate a new talking version automatically. Modify the Script Style: Adjust the GPT prompt for tone (educational, funny, storytelling). Adjust Voice Tone: Tweak ElevenLabs stability and similarity settings. Expand Platforms: Add Instagram, YouTube Shorts, or X (Twitter) posting nodes. Track Performance: Customize your Google Sheet to measure your most successful Veed.io-based videos. --- π§ Expected Outcome In just a few seconds after sending your photo and theme, this workflow β powered by Veed.io β creates a fully automated TikTok video featuring your AI avatar with natural lip-sync and voice. The result is a continuous stream of viral short videos, made without cameras, editing, or effort. --- β Import the JSON file in n8n, add your API keys (including Veed.io via FAL.ai), and start generating viral TikTok videos starring your AI avatar today! π₯ Watch This Tutorial --- π Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube
Automate Dutch Public Procurement Data Collection with TenderNed
TenderNed Public Procurement What This Workflow Does This workflow automates the collection of public procurement data from TenderNed (the official Dutch tender platform). It: Fetches the latest tender publications from the TenderNed API Retrieves detailed information in both XML and JSON formats for each tender Parses and extracts key information like organization names, titles, descriptions, and reference numbers Filters results based on your custom criteria Stores the data in a database for easy querying and analysis Setup Instructions This template comes with sticky notes providing step-by-step instructions in Dutch and various query options you can customize. Prerequisites TenderNed API Access - Register at TenderNed for API credentials Configuration Steps Set up TenderNed credentials: Add HTTP Basic Auth credentials with your TenderNed API username and password Apply these credentials to the three HTTP Request nodes: "Tenderned Publicaties" "Haal XML Details" "Haal JSON Details" Customize filters: Modify the "Filter op ..." node to match your specific requirements Examples: specific organizations, contract values, regions, etc. How It Works Step 1: Trigger The workflow can be triggered either manually for testing or automatically on a daily schedule. Step 2: Fetch Publications Makes an API call to TenderNed to retrieve a list of recent publications (up to 100 per request). Step 3: Process & Split Extracts the tender array from the response and splits it into individual items for processing. Step 4: Fetch Details For each tender, the workflow makes two parallel API calls: XML endpoint - Retrieves the complete tender documentation in XML format JSON endpoint - Fetches metadata including reference numbers and keywords Step 5: Parse & Merge Parses the XML data and merges it with the JSON metadata and batch information into a single data structure. Step 6: Extract Fields Maps the raw API data to clean, structured fields including: Publication ID and date Organization name Tender title and description Reference numbers (kenmerk, TED number) Step 7: Filter Applies your custom filter criteria to focus on relevant tenders only. Step 8: Store Inserts the processed data into your database for storage and future analysis. Customization Tips Modify API Parameters In the "Tenderned Publicaties" node, you can adjust: offset: Starting position for pagination size: Number of results per request (max 100) Add query parameters for date ranges, status filters, etc. Add More Fields Extend the "Splits Alle Velden" node to extract additional fields from the XML/JSON data, such as: Contract value estimates Deadline dates CPV codes (procurement classification) Contact information Integrate Notifications Add a Slack, Email, or Discord node after the filter to get notified about new matching tenders. Incremental Updates Modify the workflow to only fetch new tenders by: Storing the last execution timestamp Adding date filters to the API query Only processing publications newer than the last run Troubleshooting No data returned? Verify your TenderNed API credentials are correct Check that you have setup youre filter proper Need help setting this up or interested in a complete tender analysis solution? Get in touch π LinkedIn β Wessel Bulte
Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation
PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive β Download PDF β OCR text β AI normalize to JSON β Upsert Buyer (Account) β Create Opportunity β Map Products β Create OLI via Composite API β Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content β the parsed JSON (ensure itβs an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id β build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total β per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger β Download File From Google Download File From Google β Extract from File β Update File to One Drive Extract from File β Message a model Message a model β Create or update an account Create or update an account β Create an opportunity Create an opportunity β Build SOQL Build SOQL β Query PricebookEntries Query PricebookEntries β Code in JavaScript Code in JavaScript β Create Opportunity Line Items --- Quick setup checklist π Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. π IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) π§ AI Prompt: Use the strict system prompt; jsonOutput = true. π§Ύ Field mappings: Buyer tax id/name β Account upsert fields Invoice code/date/amount β Opportunity fields Product name must equal your Product2.ProductCode in SF. β Test: Drop a sample PDF β verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep βReturn only a JSON arrayβ as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields donβt support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your orgβs domain or use the Salesforce nodeβs Bulk Upsert for simplicity.