Create LinkedIn content from Telegram voice/text using Whisper, GPT-4 & Dumpling AI
Ready for 3.0What this workflow does
This AI workflow has 15 nodes and runs on Telegram events (message). Along the way it connects HTTP Request, Telegram, OpenAI and OpenAI Chat Model and 1 more. It also calls app.dumplingai.com over HTTP.
How it runs
Trigger: On Telegram events (message).
- Check Message Type (Switch): routes items into 2 branches
- Extract Text Message (Edit Fields (Set)): sets 1 field: text
- Download Telegram Audio (Telegram): work with file
- Generate Idea, Context & Image Prompt (AI Agent): runs an AI agent, with model: GPT-4 Chat Model; 3 tools (Web_search_tool, Clean Image Prompt, Image_generation_tool); memory: Simple Memory; output parser: Format Output as JSON
- Transcribe Audio to Text (OpenAI): transcribe (audio)
- Save to Airtable (Airtable): create
- Prepare Transcribed Text (Edit Fields (Set)): sets 1 field: text
- Send Confirmation to Telegram (Telegram): uses Telegram
Services it uses
HTTP calls to: app.dumplingai.com
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 (12)
- Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Http Request Tool
n8n-nodes-base.httpRequestTool - Telegram Trigger
n8n-nodes-base.telegramTrigger - Switch
n8n-nodes-base.switch - Telegram
n8n-nodes-base.telegram - OpenAI
@n8n/n8n-nodes-langchain.openAi - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Code Tool
@n8n/n8n-nodes-langchain.toolCode - Airtable
n8n-nodes-base.airtable
From the author
🧾 What this workflow does This automation turns a Telegram voice or text message into a high-quality LinkedIn post using OpenAI’s Whisper, Dumpling AI and GPT-4, and then repurposes that same message into a content idea with visual inspiration using Dumpling…