Detect toxic language in Telegram messages

Name: Detect toxic language in Telegram messages
Availability: InStock
Author: Lorena

Detect toxic language in Telegram messages preview

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

Overview

This workflow detects toxic language (such as profanity, insults, threats) in messages sent via Telegram. This blog tutorial explains how to configure the workflow nodes step-by-step.

workflow-screenshot

Telegram Trigger: triggers the workflow when a new message is sent in a Telegram chat.

Google Perspective: analyzes the text of the message and returns a probability value between 0 and 1 of how likely it is that the content is toxic.

IF: filters messages with a toxic probability value above 0.7.

Telegram: sends a message in the chat with the text "I don't tolerate toxic language" if the probability value is above 0.7.

NoOp: takes no action if the probability value is below 0.7.

Lorena

26 workflows

Nodes

n8n-nodes-base.telegramtrigger n8n-nodes-base.googleperspective n8n-nodes-base.if n8n-nodes-base.telegram n8n-nodes-base.noop

Complexity

intermediate

Published 03 Sept 2021

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/1216/1216.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Notify on menu orders via ntfy and Home Assistant TTS with daily BAC tracking

# Notify on menu orders via ntfy and Home Assistant TTS with daily BAC tracking Receive instant push notifications on your phone and voice announcements on your Google Home every time someone orders from your intranet menu — with cumulative BAC tracking per person. > **Full documentation & step-by-step setup guides:** > [📖 Notion Documentation](https://paoloronco.notion.site/Documentation-Menu-Order-Push-Notifications-Home-Assistant-TTS-BAC-32ff0ba27c328075a886d89ebfbf5ce5) > [💻 GitHub Repository](https://github.com/paoloronco/n8n-templates/tree/main/free-templates/5%20v3%20online_menu-push_notifications-homeassistant-TTS-BACcalculation) --- ## What This Workflow Does Every time a customer submits an order from your intranet menu website, this workflow: 1. Receives the order via **Webhook** 2. Logs it to an **n8n DataTable** and reads all orders for that person today 3. Calculates the cumulative **BAC** (Blood Alcohol Content) using the Widmark formula 4. Sends a **push notification** via ntfy (with order history + BAC level) 5. Triggers a **Home Assistant script** → voice announcement on Google Home **No cloud TTS fees. No external AI services. Fully self-hosted.** --- ## Flow ``` Webhook → Prepare Order → DataTable (INSERT) → Read Today's Orders → BAC Calculator → ntfy Push Notification → Home Assistant TTS ``` --- ## Example Output **Push notification (ntfy app):** ``` 🛎 Order from Mario Mario: 1x Pizza, 2x Beer 33cl 🕐 12:30 📋 Ordered before: - 1x Prosecco 🕐 11:45 🍸 BAC ~0.54 g/L 🔴 ``` **Google Home voice announcement:** ``` Mario has ordered Pizza ``` --- ## Prerequisites Before importing this workflow, you need: - A running **n8n** instance (self-hosted or cloud) reachable from the internet - **Home Assistant** on your local network (e.g. `homeassistant.local:8123`) - At least one **Google Home** (or Chromecast-capable) device added to HA via the Google Cast integration - **ntfy** deployed via Docker (self-hosted push notification server) - A public HTTPS URL for ntfy — recommended via **Cloudflare Tunnel** (no open ports needed) - An Android or iOS device with the **ntfy app** installed --- ## Credentials Required | Credential | Used For | | ------------------------------------------------------ | ---------------------------------------- | | **Home Assistant** | Calling the `annuncia_ordine` TTS script | | **Header Auth** (`Authorization: Bearer <ntfy_token>`) | Sending authenticated requests to ntfy | --- ## n8n DataTable Schema Create a DataTable in **n8n → Data → Tables** with these columns: | Column | Type | Description | | -------------- | ------ | ------------------------------------------------------ | | `item` | Text | Full order string (e.g. "2x Negroni, 1x Messina 33cl") | | `person` | Text | Normalised person name | | `alcol_grammi` | Number | Total grams of alcohol for this order | | `data` | Text | ISO date (YYYY-MM-DD) | | `orario` | Text | Time string from the order | Copy the DataTable ID and paste it into the DataTable nodes inside the workflow. --- ## Webhook Payload Your menu website must POST this JSON to the Webhook Production URL: ```json { "name": "Mario", "time": "26/03/2026, 12:30:00", "order": [ { "section": "Food", "name": "Pizza", "details": "", "quantity": 1 }, { "section": "Drinks", "name": "Beer", "details": "33cl", "quantity": 2 } ], "total": 3 } ``` --- ## Setup Steps ### 1. Deploy ntfy (self-hosted push notifications) Add ntfy to your `docker-compose.yml`: ```yaml ntfy: image: binwiederhier/ntfy command: serve volumes: - ./ntfy/config:/etc/ntfy - ./ntfy/data:/var/lib/ntfy ports: - "8095:80" ``` In `server.yml`, set `auth-default-access: deny-all`. Then create an admin user and generate a token: ```bash docker exec -e NTFY_PASSWORD="your_password" ntfy ntfy user add --role=admin admin docker exec ntfy ntfy token add admin ``` ### 2. Expose ntfy over HTTPS (Cloudflare Tunnel) Add an ingress rule to your Cloudflare Tunnel config: ```yaml - hostname: ntfy.YOUR_DOMAIN.com service: http://localhost:8095 ``` ### 3. Configure Home Assistant TTS In HA, go to **Settings → Automations & Scenes → Scripts → Add script → Edit in YAML** and paste: ```yaml alias: annuncia_ordine sequence: - action: tts.speak target: entity_id: tts.google_translate_en_com data: media_player_entity_id: media_player.YOUR_GOOGLE_HOME_ENTITY message: "{{ message }}" language: it mode: single ``` > Replace `media_player.YOUR_GOOGLE_HOME_ENTITY` with your actual entity ID. Then go to your HA profile → **Security → Long-lived access tokens** → create and copy a token. ### 4. Import and configure the workflow 1. Import the workflow JSON into n8n 2. Create the **DataTable** (columns listed above) — copy its ID 3. Create the **Header Auth** credential for ntfy: - Header Name: `Authorization` - Header Value: `Bearer YOUR_NTFY_TOKEN` 4. Create the **Home Assistant** credential: - Host: `http://homeassistant.local:8123` - Access Token: your HA long-lived token 5. In the `ntfy notification` node, replace `YOUR_TOPIC` in the URL 6. In the `Home Assistant TTS` node, set the `message` attribute expression: ``` ={{ $('Webhook').item.json.body.nome }} has ordered {{ $('Webhook').item.json.body.ordine[0].nome }} ``` 7. Activate the workflow and copy the **Webhook Production URL** ### 5. Configure your menu website Set the webhook URL in your menu site config: ```js // menu-data.js "orderWebhook": "https://YOUR_N8N_DOMAIN/webhook/menu" ``` --- ## BAC Calculation (Widmark Formula) ``` BAC [g/L] = total_alcohol_grams_today / (70 × 0.68) ``` Assumes ~70 kg body weight. Italian legal driving limit: **0.5 g/L** | Emoji | Level | BAC | | ----- | ---------- | ------------- | | ⬜ | None | 0 g/L | | 🟢 | Low | < 0.2 g/L | | 🟡 | Warning | 0.2 – 0.5 g/L | | 🔴 | Over limit | > 0.5 g/L | BAC is **cumulative per day per person** and resets automatically the next day. --- ## Customization | What | How | | ----------------------------------------- | ------------------------------------------------------------ | | Change the TTS message | Edit the `message` expression in the HA TTS node | | Announce all ordered items | Use `$json.body.ordine.map(i => i.quantita + ' ' + i.nome).join(', ')` | | Change TTS language | Edit `language` in the `annuncia_ordine` HA script | | Announce on multiple Google Home devices | Add multiple `media_player_entity_id` entries to the HA script | | Disable TTS (keep only push notification) | Remove or deactivate the `Home Assistant TTS` node | --- ## Security | Layer | Mechanism | | -------------------- | ---------------------------------------------------- | | Transport (ntfy) | HTTPS via Cloudflare Tunnel | | ntfy access | `auth-default-access: deny-all` — no anonymous reads | | n8n → ntfy | Dedicated Bearer token (revokable, no expiry) | | n8n → Home Assistant | Long-lived access token | | Mobile app | Username/password on the ntfy server | --- ## Documentation & Source | | | | ------------------------ | ------------------------------------------------------------ | | 📖 **Full documentation** | [Notion — step-by-step setup guides](https://paoloronco.notion.site/Documentation-Menu-Order-Push-Notifications-Home-Assistant-TTS-BAC-32ff0ba27c328075a886d89ebfbf5ce5) | | 💻 **GitHub Repository** | [paoloronco/n8n-templates](https://github.com/paoloronco/n8n-templates/tree/main/free-templates/5%20v3%20online_menu-push_notifications-homeassistant-TTS-BACcalculation) | ## Related Resources - [ntfy.sh documentation](https://docs.ntfy.sh) - [Home Assistant TTS documentation](https://www.home-assistant.io/integrations/tts/) - [Home Assistant Scripts](https://www.home-assistant.io/integrations/script/) - [Google Cast integration](https://www.home-assistant.io/integrations/cast/) - [n8n Home Assistant node](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.homeassistant/)

View

Validate QR tickets in real time with Google Forms and Sheets

## Automated QR Ticket Scanner & Validator This workflow is the perfect companion to the "Automated e-Ticket PDF Generator". It acts as a lightweight, automated check-in system for events. By pairing a simple Google Form with a mobile scanning app, it validates QR codes against your master database in real-time and logs the attendance status. ### How it works 1. **Trigger:** The workflow triggers instantly when a new response is submitted to a Google Form (which acts as your QR code scanner input). 2. **Data Extraction:** It isolates the scanned QR code string from the new Google Sheet row. 3. **Database Lookup:** It cross-references the scanned code with your Master Participant Database in Google Sheets. 4. **Validation (Switch):** A logic node checks if the scanned ticket exists and matches the database. 5. **Log Results:** - **VALID:** If matched, it logs the participant's details into a "Scan Results" sheet with a "VALID" status. - **INVALID:** If not matched, it logs the scanned code with an "INVALID" status, alerting you to an unregistered ticket. ### Field Setup (Pro-Tip) To make this work seamlessly at an actual event venue: 1. **Create a Google Form:** Make a simple form with one short-answer text input for the QR code. 2. **Use "Scan to Web" App:** Install the [Scan to Web](https://play.google.com/store/apps/details?id=com.berrywing.scantoweb) app (or a similar keyboard scanner app) on an Android smartphone. 3. **Scan Away:** Open your Google Form link on the phone, tap the text input field, and use the app to scan the attendee's physical or digital QR code. The app will automatically type the code and submit the form, triggering this n8n workflow instantly! ### Requirements - A Google Workspace account (Google Forms & Google Sheets). - A basic understanding of mapping Google Sheets columns in n8n. - An Android smartphone with the "Scan to Web" app installed for field scanning.

View

Read palm lines and send AI reports via LINE, Gemini, Gmail and Calendar

# Template description (paste this into the n8n Creator Dashboard) --- ## Who is this for This workflow is for anyone who wants to offer a fun, automated palm reading experience through LINE — Japan's dominant messaging app with over 90 million active users. It suits indie developers, wellness creators, fortune-telling services, or anyone curious about combining AI vision with multi-channel automation. ## What this workflow does When a user sends a photo of their palm via LINE, the workflow springs into action across five tools: 1. **LINE Messaging API** receives the image via webhook 2. **Google Gemini** analyzes the palm and produces three outputs: a short LINE-ready summary (under 100 characters), a full reading covering the life line, heart line, head line, and fate line, and three lucky day suggestions with reasons 3. **LINE reply** sends the short summary back to the user instantly 4. **Gmail** delivers a formatted HTML report with the complete reading to a specified address 5. **Google Calendar** registers the three lucky days as calendar events so the user never forgets them Non-image messages (text, stickers) are caught early and trigger a friendly prompt asking the user to send a palm photo instead. ## How to set up 1. Open the **Set config variables** node and fill in your `LINE_CHANNEL_ACCESS_TOKEN`, `GMAIL_FROM`, `GMAIL_TO`, and `GOOGLE_CALENDAR_ID` 2. Connect your **Google Gemini API** credential to the Google Gemini Chat Model node 3. Connect your **Gmail OAuth2** credential to the Gmail node 4. Connect your **Google Calendar OAuth2** credential to the Calendar node 5. Activate the workflow and copy the webhook URL 6. Paste the webhook URL into your LINE Developer Console under the Messaging API channel settings ## Requirements - LINE Developer account and a Messaging API channel (free) - Google Gemini API key (free tier available at Google AI Studio) - Gmail account with OAuth2 set up in n8n - Google Calendar with OAuth2 set up in n8n ## How to customize - **Change the reading language**: edit the prompt in the **Analyze palm lines with Gemini** node — swap English for Japanese, Spanish, or any language Gemini supports - **Adjust the report destination**: update `GMAIL_TO` in the config node to send the report to the user's own address (you could collect it via a prior LINE conversation) - **Change lucky day timing**: the Calendar node currently schedules events starting 7 days from now — adjust the `$now.plus()` expression to fit your use case - **Extend the AI prompt**: add astrology, tarot, or numerology sections to the Gemini prompt for a richer reading experience

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Detect toxic language in Telegram messages

Workflow preview

Important notice

Overview