Automations
4 min read

n8n Workflow: Convert RSS Feeds into Podcasts with Gemini, Kokoro TTS & FFmpeg

Dev Shabbir
Dev Shabbir
March 5, 2026

Imagine turning your favorite blogs, news sites, or industry updates into a personalized podcast—without lifting a finger. That’s exactly what this powerful n8n workflow does: it converts RSS feeds into a podcast with Google Gemini, Kokoro TTS, and FFmpeg, automating the entire process from content ingestion to audio delivery.

Whether you're a freelancer repurposing client content, a small business owner building thought leadership, or a developer exploring AI-driven automation, this guide gives you everything you need—including a free, ready-to-import n8n template—to launch your own automated podcast pipeline in under an hour.

🚀 Instant Access: Get the Template

Skip the setup and jump straight into automation. Our pre-built n8n workflow includes all nodes, error handling, and configuration tips.

Install this Workflow Now

What Problem Does This Workflow Solve?

Creating consistent podcast content is time-consuming. You have to curate articles, write scripts, record voiceovers, edit audio, and publish—all manually. For busy professionals, this often means podcasts get deprioritized or abandoned altogether.

This n8n RSS to podcast automation solves five key pain points:

  • Eliminates manual content curation by pulling fresh posts directly from any RSS feed.
  • Removes technical barriers—no coding required to integrate AI, TTS, and audio tools.
  • Scales content repurposing for agencies, newsletters, or multilingual audiences.
  • Reduces production time from hours per episode to minutes.

How the Automation Works: A Step-by-Step Breakdown

This workflow combines four core technologies into a seamless pipeline:

1. RSS Feed Ingestion

The RSS Read node fetches new articles from your chosen feed (e.g., TechCrunch, your blog, or a niche newsletter). It runs on a schedule—daily, hourly, or every few minutes—so you never miss an update.

2. AI-Powered Summarization with Google Gemini

Raw RSS content is often too long for a podcast. That’s where Google Gemini comes in. Using the @n8n/n8n-nodes-langchain.lmChatGoogleGemini node, the workflow sends each article to Gemini with a prompt like:

"Summarize this article in 150 words, focusing on key insights and actionable takeaways. Write in a conversational tone suitable for a podcast."

This ensures your podcast episodes are concise, engaging, and audience-ready—without manual editing.

3. Natural-Sounding Voice with Kokoro TTS

Next, the summarized text is sent to Kokoro TTS (via HTTP Request or local inference) to generate high-quality speech. Kokoro offers expressive, human-like voices in multiple languages and accents—perfect for professional podcasts.

Pro Tip: Use the Set node to dynamically assign voice parameters (speed, pitch, speaker) based on content type—e.g., formal for business feeds, upbeat for lifestyle blogs.

4. Audio Processing with FFmpeg

The raw audio from Kokoro may need trimming, normalization, or format conversion. The Execute Command node runs FFmpeg to:

  • Convert WAV to MP3 for smaller file sizes
  • Add intro/outro music (optional)
  • Normalize volume levels

5. Delivery & Distribution

Finally, the processed audio file can be:

  • Uploaded to cloud storage (Google Drive, S3)
  • Sent via Telegram or email as a notification
  • Posted directly to podcast hosts (via API, with custom Code node)

Why This Stack? Gemini + Kokoro + FFmpeg

Tool Role Advantage
Google Gemini Content summarization Understands context, extracts insights, writes conversationally
Kokoro TTS Text-to-speech Open-weight, low-latency, natural voices (vs. robotic alternatives)
FFmpeg Audio processing Free, powerful, scriptable—handles any audio format

Real-World Use Cases

🎯 For Freelancers & Agencies

Offer "Content-to-Podcast" as a premium service. Turn client blogs into weekly audio briefings—no extra recording time needed.

📈 For Small Businesses

Repurpose your newsletter or product updates into a branded podcast for LinkedIn, Spotify, or your website—boosting SEO and engagement.

🌍 For Multilingual Audiences

Use Gemini to translate summaries, then Kokoro to speak them in Spanish, French, or Mandarin—all within the same workflow.

Get Started in 3 Steps

  1. 1

    Import the Template

    Click the CTA below to get the full n8n JSON workflow. It includes all nodes, error handling, and batch processing logic.

  2. 2

    Configure Your Feeds & APIs

    Add your RSS URL, Gemini API key, and Kokoro endpoint (local or cloud). The template guides you through each step.

  3. 3

    Schedule & Go!

    Set your trigger (daily at 8 AM, for example), and let n8n handle the rest. Check your Telegram for new episodes.

⚡ Ready to Automate Your Podcast?

Stop wasting hours on manual production. This workflow saves 5+ hours per week for content creators—scale your output without scaling your effort.

Install this Workflow Now

Troubleshooting & Best Practices

  • Rate Limits: Gemini has usage caps. Use the Split In Batches node to process feeds in chunks.
  • Audio Quality: Test Kokoro voices with short samples first. Adjust speed to 0.95x for a more natural pace.
  • Storage: Audio files add up. Use the Read/Write File node to auto-delete temp files after upload.

For deeper dives, check out our guides on n8n + Gemini setup and choosing the right TTS engine. And if you're new to n8n, start with What Is n8n?.