Transcribe Telegram voice notes to Google Docs with OpenAI & DeepSeek summaries
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 7 nodes and runs on Telegram events. Along the way it connects Telegram, OpenAI, DeepSeek Chat Model and Google Drive.
How it runs
Trigger: On Telegram events.
- Telegram: uses Telegram
- OpenAI: uses OpenAI
- Google Drive: uses Google Drive
- AI Agent: runs an AI agent, with model: DeepSeek Chat Model
- Google Drive: uses Google Drive
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent2 (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent2 (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (6)
- Telegram
n8n-nodes-base.telegram - OpenAI
@n8n/n8n-nodes-langchain.openAi - DeepSeek Chat Model
@n8n/n8n-nodes-langchain.lmChatDeepSeek - AI Agent
@n8n/n8n-nodes-langchain.agent - Telegram Trigger
n8n-nodes-base.telegramTrigger - Google Drive
n8n-nodes-base.googleDrive
From the author
This n8n workflow automates the process of transcribing a voice message received via Telegram, summarizing the transcription using an AI model, and then saving both the transcription and the summary to separate Google Docs in Google Drive. Here's a breakdown…