Transcribing Telegram voice messages using Whisper and Gemini with a fallback mechanism
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 20 nodes and runs on Telegram events (message). Along the way it connects Telegram, OpenAI and Google Gemini.
How it runs
Trigger: On Telegram events (message).
- Access Check (If): checks a condition and branches into true / false
- Determining The Type Of Document (Switch): routes items into 2 branches
- MSG - Access denied! (Telegram): uses Telegram
- Assigning file_id For Voice (Edit Fields (Set)): sets 1 field: file_id
- Assigning file_id For Audio (Edit Fields (Set)): sets 1 field: file_id
- MSG - No file! (Telegram): uses Telegram
- Transcription Decision Node (If): checks a condition and branches into true / false
- Get File GPT (Telegram): work with file
- MSG - File not recognized (Telegram): uses Telegram
- Transcription by OpenAi (OpenAI): transcribe (audio)
…plus 9 more steps. See the full node list below.
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 (8)
- Telegram Trigger
n8n-nodes-base.telegramTrigger - Telegram
n8n-nodes-base.telegram - If
n8n-nodes-base.if - Switch
n8n-nodes-base.switch - Edit Fields (Set)
n8n-nodes-base.set - OpenAI
@n8n/n8n-nodes-langchain.openAi - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Code
n8n-nodes-base.code
From the author
🎙️ n8n Workflow: Voice Message Transcription with Access Control This n8n workflow enables automated transcription of voice messages in Telegram groups with built-in access control and intelligent fallback mechanisms. It's designed for teams that need to…