Convert Documents to Podcast Audio with GPT-4o & OpenAI TTS

This n8n workflow provides an end-to-end automation for converting written documents into professional multi-speaker podcast audio. It monitors a Google Drive folder for new documents, extracts text, uses GPT-4o to generate a detailed podcast script with multiple speakers, produces individual audio segments via OpenAI TTS, stores them, concatenates into a full episode, and saves the final audio back to Google Drive.

Key benefits include significant time savings for content creators, podcasters, and marketers by eliminating manual scripting, recording, and editing. It ensures consistent high-quality output with dynamic voices, making it ideal for newsletters, articles, reports, or blogs turned into engaging audio content.

Use cases: Journalists automating news podcasts from articles; educators creating audio lessons from docs; businesses producing internal comms or marketing podcasts; solopreneurs scaling audio content production without a team.

Requires self-hosted n8n with community nodes, Google Drive setup, and OpenAI API keys. Setup takes ~15 minutes.