This workflow automates the processing of incoming Telegram messages, whether voice or text, to generate engaging social media content and visual images. It begins by listening for new messages via a Telegram trigger. If a voice message is received, the workflow fetches the audio file and transcribes it into text using OpenAI’s Whisper API. If a text message is received, it proceeds directly. The text content is then processed by an AI agent that researches the topic using SerpAPI, creates SEO-optimized social media posts, and generates detailed prompts for image creation. An image is subsequently produced through a Hugging Face inference API, completing the content creation cycle. This automation is ideal for social media managers, marketing teams, or content creators who want to streamline content generation from voice or text interactions on Telegram, ensuring timely, relevant, and engaging posts with compelling visuals.
Automated Voice and Text Message Processing with AI
Node Count | 11 – 20 Nodes |
---|---|
Nodes Used | @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmChatOpenAi, @n8n/n8n-nodes-langchain.openAi, @n8n/n8n-nodes-langchain.outputParserStructured, @n8n/n8n-nodes-langchain.toolSerpApi, extractFromFile, httpRequest, set, stickyNote, switch, telegram, telegramTrigger |
Reviews
There are no reviews yet.