AI Chatbot Agent for Telegram (Text & Voice)

Unlock 24/7 Automated Conversations with this AI Agent

This workflow transforms your Telegram bot into a powerful, multimodal AI agent. It can understand and respond to users via both text and voice messages, providing a seamless and natural conversational experience. The agent is powered by OpenAI's GPT-4o, leveraging its advanced reasoning capabilities, and uses the Whisper API for highly accurate speech-to-text conversion. With built-in conversational memory, it can recall previous parts of the chat, leading to more helpful and contextually relevant interactions.

Key Features & Benefits

• Multimodal Input: Engages users how they prefer, accepting both standard text and voice notes.
• AI-Driven Conversations: Utilizes OpenAI's GPT-4o for smart, human-like responses.
• Voice Recognition: Accurately transcribes spoken messages into text for the AI to process.
• Conversational Memory: Remembers the last 10 interactions per user for context-rich conversations.
• Customizable Persona: Easily edit the system prompt to define your agent's personality, tone, and instructions.
• Robust Error Handling: Includes logic to automatically correct and resend messages with formatting issues.

• An n8n instance (Cloud or self-hosted).
• An OpenAI API Key with access to GPT-4o and the Whisper audio transcription model.
• A Telegram Bot with its API Token.

1. Import the workflow JSON into your n8n instance.
2. Configure the 'Listen for incoming events' Telegram Trigger node with your Telegram Bot credentials.
3. In the other Telegram nodes ('Download voice file', 'Send final reply', etc.), select the same credentials from the dropdown menu.
4. Configure the 'OpenAI Chat Model' and 'Convert audio to text' nodes with your OpenAI API credentials.
5. (Optional) Customize the systemMessage in the 'AI Agent' node to define your chatbot's persona and rules.
6. Activate the workflow and start a conversation with your bot on Telegram to test it.