Telegram chatbot with voice recognition and message batching using OpenAI
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 26 nodes and runs on Telegram events (message). Along the way it connects Telegram, OpenAI, Google Sheets and Embeddings OpenAI and 2 more.
How it runs
Trigger: On Telegram events (message).
- Link Filter (If): checks a condition and branches into true / false
- Get Audio File (Telegram): work with file
- Pass text message (Edit Fields (Set)): sets 3 fields: processedMessage, sessionId, name
- Transcribe a recording (OpenAI): transcribe (audio)
- Merge: merges the data from its input branches
- Transcript Result (Edit Fields (Set)): sets 3 fields: processedMessage, sessionId, name
- Transcript Error Output (Edit Fields (Set)): sets 2 fields: error, sessionId
- Edit Fields (Edit Fields (Set)): sets 2 fields: processedMessage, sessionId
- Append row in sheet (Google Sheets): append
- Get row(s) in sheet (Google Sheets): uses Google Sheets
…plus 11 more steps. See the full node list below.
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 Agent (v1.7): 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 Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (14)
- Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - Merge
n8n-nodes-base.merge - Telegram
n8n-nodes-base.telegram - OpenAI
@n8n/n8n-nodes-langchain.openAi - Google Sheets
n8n-nodes-base.googleSheets - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - Wait
n8n-nodes-base.wait - Code
n8n-nodes-base.code - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Telegram Trigger
n8n-nodes-base.telegramTrigger
From the author
This Telegram workflow batches rapid-fire messages from the same user into one prompt (20–30s debounce), then sends a single AI reply. It uses two Google Sheets: - Message Retention (date | userid | message) — queues incoming messages. - Message Checkup…