Build a voice & text Telegram Bot with GPT-4.1-Mini and Gemini transcription
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 14 nodes and runs on Telegram events (message). Along the way it connects Telegram, OpenAI Chat Model, Google Gemini and OpenAI and 1 more.
How it runs
Trigger: On Telegram events (message).
- If: checks a condition and branches into true / false
- Get a file (Telegram): work with file
- Guardrails: uses Guardrails, with model: OpenAI Chat Model
- Transcribe a recording (Google Gemini): work with audio
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; memory: Simple Memory
- Send a text message (Telegram): uses Telegram
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; memory: Simple Memory
- Send a text message (Telegram): uses Telegram
- Generate audio (OpenAI): work with audio
- Send an audio file (Telegram): send audio
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (9)
- Telegram Trigger
n8n-nodes-base.telegramTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Telegram
n8n-nodes-base.telegram - If
n8n-nodes-base.if - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - OpenAI
@n8n/n8n-nodes-langchain.openAi - Guardrails
@n8n/n8n-nodes-langchain.guardrails
From the author
How it works: This Telegram automation works with voice and text messages given to the Telegram bot, and it returns the response in voice form if the input is in voice form. If the input is in text form, it will return a response in text form. Use Cases: -…