What This Workflow Does
This automation transforms RSS feeds into professional-quality podcasts without manual intervention. It solves the time-consuming process of manually creating audio content from written sources, enabling businesses and content creators to expand their reach into the growing podcast market with minimal effort.
The workflow fetches latest articles from specified RSS feeds, uses Google Gemini to generate a cohesive script, converts the text to natural-sounding speech with Kokoro TTS, then assembles the audio files with FFmpeg into a polished podcast episode. This end-to-end automation can produce daily or weekly episodes consistently without human involvement.
How It Works
1. RSS Feed Aggregation
The workflow begins by fetching the latest articles from your configured RSS feeds. It can process multiple sources simultaneously, filtering for relevant content based on your criteria.
2. AI Content Summarization
Google Gemini analyzes and summarizes the collected articles, creating a cohesive narrative script. The AI can be instructed to maintain specific tones, include key points, or follow particular formatting guidelines.
3. Text-to-Speech Conversion
Kokoro TTS transforms the generated script into natural-sounding audio. You can customize voice characteristics like gender, accent, and speaking rate to match your brand identity.
4. Audio Post-Production
FFmpeg processes the audio files, adding intro/outro music, adjusting volume levels, and applying noise reduction. The final output is saved in standard podcast formats ready for distribution.
Who This Is For
This automation is ideal for media companies, content marketers, and businesses with regular publications. News organizations can create daily briefings, bloggers can repurpose content for audio platforms, and educational providers can transform articles into learning resources.
Marketing teams use this to extend content reach, while SaaS companies provide automated podcast feeds as a customer value-add. The solution works for any organization wanting to establish or expand their audio presence without investing in studio production.
What You'll Need
- n8n instance (cloud or self-hosted)
- Google Gemini API access
- Kokoro TTS or similar text-to-speech service
- FFmpeg installed on your server
- RSS feed URLs for your content sources
- Storage solution for audio files (AWS S3, Google Cloud, etc.)
Pro tip: Start with free tiers of each service to test the workflow before committing to paid plans. Most providers offer sufficient capacity for initial testing.
Quick Setup Guide
- Download and import the JSON template into your n8n instance
- Configure your RSS feed sources in the first module
- Enter your Google Gemini API credentials
- Set up Kokoro TTS with your preferred voice parameters
- Adjust FFmpeg settings for your desired audio output format
- Test with a single article before processing full feeds
- Schedule the workflow for daily or weekly execution
Key Benefits
Save 10+ hours weekly by automating what would otherwise require manual scripting, recording, and editing for each episode.
Expand audience reach by making your content accessible to podcast listeners without creating additional original material.
Maintain consistent publishing with automated daily or weekly episodes that keep your audience engaged.
Reduce production costs by eliminating the need for voice talent, recording equipment, and audio engineers.
Repurpose existing content to maximize ROI on your written articles and blog posts.