n8n Telegram Bot Workflows v2 — KI-Report

key for audio transcription (voice messages)\n Perplexity AI: API key for web search\n ScrapeGraphAI: API key for web scraping\n Google Services: OAuth2 credentials for Gmail, Drive, Docs, Sheets, Slides, Calendar\n Qdrant: API endpoint and access key for RAG\n Cohere: API key for reranking in RAG\n OpenRouter: API key for Gemini language model (if using)\n PostgreSQL: Database connection details for chat memory\n FTP Server: Credentials to upload image files\n\nConfigure Tools and Sub-Workflows\n Adjust the \“OpenClaw Agents\“ node with your preferred AI models, tools, and services\n Customize sub-workflows as needed for specific tasks (e.g., image/video generation)\n\nTest and Deploy\n Test the workflow using different types of messages (text, voice, images) to ensure proper handling\n Deploy the workflow in n8n and interact with it via Telegram\n“,
„createdAt“: „2026-03-14T09:57:43.000Z“
},
{
„id“: 13990,
„name“: „Telegram AI Agent for Google Workspace Automation (Gmail, Calendar, Drive)“,
„totalViews“: 28,
„price“: 0,
„purchaseUrl“: null,
„description“: „This workflow implements an advanced AI automation agent that interacts with users through Telegram and integrates multiple AI models, external tools, and cloud services to automate complex tasks.\n\nThe agent can autonomously decide which tools to use to complete the request. It has access to multiple integrations, including:\n\nGmail (read, send, reply, draft emails)\nGoogle Calendar (create, delete, check availability)\nGoogle Drive, Docs, Sheets, and Slides\nWeb search and web scraping tools\nRAG (Retrieval-Augmented Generation) using a vector database Here how set up\nImage and video analysis tools\nMathematical calculator tools\nCustom sub-workflows and MCP integrations\n\nThe system also includes persistent chat memory stored in PostgreSQL, allowing the AI to remember previous interactions and maintain conversation context.\n\nFinally, the workflow generates a response and sends it back to the user via Telegram. If the input was voice-based, the response can also be converted into audio and returned as a voice message.\n\nAn escalation mechanism allows the system to transfer the conversation to a human operator when needed.\n\nKey Advantages\n\n1. ✅ Multimodal Interaction\n\nThe workflow supports text, voice, and image inputs, allowing users to interact with the system naturally.\n\n2. ✅ AI-Powered Automation\n\nThe integrated AI agent can autonomously decide which tools to use to solve tasks, reducing manual intervention and enabling intelligent automation.\n\n3.✅ Deep Integration with Google Workspace\n\nThe workflow can manage emails, documents, spreadsheets, presentations, and calendar events directly through AI commands.\n\n4. ✅ Retrieval-Augmented Knowledge (RAG)\n\nThe system can access external knowledge sources through a vector database, improving response accuracy and enabling knowledge-based answers.\n\n5. ✅ Persistent Memory\n\nConversation history is stored in PostgreSQL, allowing the agent to maintain context and provide more relevant responses over time.\n\n6. ✅ Web Intelligence\n\nBuilt-in web search and scraping capabilities allow the agent to gather real-time information from the internet.\n\n7. ✅ Voice Response Capability\n\nThe system can generate audio responses, creating a more natural conversational experience.\n\n8. ✅ Modular and Scalable Architecture\n\nThe workflow is highly modular, allowing new tools, agents, and services to be added easily.\n\n9. ✅ Human Escalation\n\nWhen automation is not sufficient, the system can escalate the conversation to a human operator.\n\n10. ✅ Fully Automated Digital Assistant\n\nOverall, the workflow acts as a fully autonomous AI assistant capable of performing complex operational tasks across multiple platforms.\n\nHow it works\n\nThis workflow is a comprehensive Telegram-based AI orchestrator that simulates an OpenClaw-style multi-agent architecture. When a user sends a message to the Telegram bot, the workflow:\n\nReceives and authorizes the message through a Telegram trigger, checking if the user ID matches an authorized user (configured in the Code node)\n\nRoutes different content types using a Switch node that detects whether the incoming message contains text, voice, or images:\n Text messages: Directly passed to the orchestrator\n Voice messages: Downloaded and transcribed using OpenAI’s audio transcription\n Images: Downloaded, uploaded to an FTP server, and transformed into a URL for processing\n\nFeeds the processed input (text, transcribed voice, or image URL with caption) into the \“OpenClaw Agents\“ node – an AI agent configured with Gemini as the language model and Postgres for chat memory\n\nOrchestrates specialized sub-agents through the main AI agent, which can delegate tasks to multiple tools:\n Research and web search (Perplexity AI)\n Web scraping (ScrapeGraphAI)\n Google services (Gmail, Drive, Docs, Sheets, Slides, Calendar)\n RAG (Qdrant vector store with Cohere reranker)\n Image/Video generation (via sub-workflow)\n Calculator\n Telegram communication tools\n\nHandles response delivery based on the original message type:\n If the original message was voice, the workflow generates an audio response using OpenAI TTS and sends it back as audio\n Otherwise, sends a text response via Telegram\n\nIncludes escalation capabilities through a human-in-the-loop tool for situations requiring human intervention\n\nSet up steps\n\nConfigure Telegram Bot\n Create a Telegram bot via BotFather to get a bot token\n Set up Telegram credentials in n8n\n Replace XXX in the Code node with your authorized Telegram user ID\n\nSet up API Keys and Credentials\n OpenAI: API key for audio transcription (voice messages)\n Perplexity AI: API key for web search\n ScrapeGraphAI: API key for web scraping\n Google Services: OAuth2 credentials for Gmail, Drive, Docs, Sheets, Slides, Calendar\n Qdrant: API endpoint and access key for RAG\n Cohere: API key for reranking in RAG\n OpenRouter: API key for Gemini language model (if using)\n PostgreSQL: Database connection details for chat memory\n FTP Server: Credentials to upload image files\n\nConfigure Tools and Sub-Workflows\n Adjust the \“OpenClaw Agents\“ node with your preferred AI models, tools, and services\n Customize sub-workflows as needed for specific tasks (e.g., image/video generation)\n\nTest and Deploy\n Test the workflow using different types of messages (text, voice, images) to ensure proper handling\n Deploy the workflow in n8n and interact with it via Telegram“,
„createdAt“: „2026-03-14T09:57:43.000Z“
},
{
„id“: 13989,
„name“: „Telegram AI Agent for Google Workspace Automation (Gmail, Calendar, Drive)“,
„totalViews“: 28,
„price“: 0,
„purchaseUrl“: null,
„description“: „This workflow implements an advanced AI automation agent that interacts with users through Telegram and integrates multiple AI models, external tools, and cloud services to automate complex tasks.\n\nThe agent can autonomously decide which tools to use to complete the request. It has access to multiple integrations, including:\n\nGmail (read, send, reply, draft emails)\nGoogle Calendar (create, delete, check availability)\nGoogle Drive, Docs, Sheets, and Slides\nWeb search and web scraping tools\nRAG (Retrieval-Augmented Generation) using a vector database Here how set up\nImage and video analysis tools\nMathematical calculator tools\nCustom sub-workflows and MCP integrations\n\nThe system also includes persistent chat memory stored in PostgreSQL, allowing the AI to remember previous interactions and maintain conversation context.\n\nFinally, the workflow generates a response and sends it back to the user via Telegram. If the input was voice-based, the response can also be converted into audio and returned as a voice message.\n\nAn escalation mechanism allows the system to transfer the conversation to a human operator when needed.\n\nKey Advantages\n\n1. ✅ Multimodal Interaction\n\nThe workflow supports text, voice, and image inputs, allowing users to interact with the system naturally.\n\n2. ✅ AI-Powered Automation\n\nThe integrated AI agent can autonomously decide which tools to use to solve tasks, reducing manual intervention and enabling intelligent automation.\n\n3.✅ Deep Integration with Google Workspace\n\nThe workflow can manage emails, documents, spreadsheets, presentations, and calendar events directly through AI commands.\n\n4. ✅ Retrieval-Augmented Knowledge (RAG)\n\nThe system can access external knowledge sources through a vector database, improving response accuracy and enabling knowledge-based answers.\n\n5. ✅ Persistent Memory\n\nConversation history is stored in PostgreSQL, allowing the agent to maintain context and provide more relevant responses over time.\n\n6. ✅ Web Intelligence\n\nBuilt-in web search and scraping capabilities allow the agent to gather real-time information from