Convert PDF to AI Podcasts with Gemini & TTS

This n8n workflow transforms static PDF documents into dynamic, conversational podcasts. It begins by extracting text from uploaded PDFs, then leverages Google Gemini AI to generate a natural-sounding podcast script. The script is converted to high-quality speech using Google's Text-to-Speech with customizable voices like Kore (professional), Aoede (conversational), or Laomedeia (energetic). Audio is processed into WAV format and saved for easy distribution.

Ideal for content creators, educators, researchers, and marketers, this workflow saves hours of manual scriptwriting and editing. It solves the challenge of repurposing written content into accessible audio, making documents perfect for podcasts, audiobooks, or on-the-go learning. The automation ensures consistent, professional results with minimal effort.

Setup requires a Google Gemini API key from AI Studio, configured in n8n. Test with sample PDFs, adjust prompts and voices as needed, and integrate into your content pipeline for scalable audio production.