AI-Powered Podcast Creation: Idea, Script, and Audio Generation - n8n Workflow

• Solo podcasters and content teams seeking to rapidly prototype short audio segments.


• Users interested in leveraging large language model agents within an n8n workflow.


• Developers needing advanced n8n templates for multi-step AI orchestration.


• Anyone looking to automate text-to-speech (TTS) processes using an n8n node.

This robust n8n workflow offers a complete 'Podcast on Autopilot' solution, taking a simple topic and transforming it into a broadcast-ready audio file without manual intervention. The challenge of creating engaging, high-quality audio content quickly is solved by intelligently chaining specialized AI models. The n8n automation leverages OpenAI (GPT-4) for generating creative, targeted podcast ideas and Anthropic (Claude Sonnet) for meticulously crafting a natural, human-like script, adhering to the complex tonality of successful monologues like Joe Rogan's. Once the script is finalized, the workflow utilizes Eleven Labs for generating high-fidelity audio. This particular n8n workflow demonstrates the power of integrating multiple state-of-the-art services, proving that complex creative tasks can be reliably automated using n8n templates.

The process begins with the When chat message received n8n trigger, initiating the entire n8n workflow based on a simple input topic or seed idea.

1. Idea Generation: The input topic flows into the Podcast Idea/Topic Agent (powered by GPT-4 via the OpenAI Chat Model n8n node). This agent's prompt is configured to produce a single, compelling episode concept tailored for a monologue show, complete with a hook and takeaway.


2. Scriptwriting: The generated idea is passed to the Podcast Script Agent (powered by Claude Sonnet via the Anthropic Chat Model n8n node). This agent specializes in turning the raw concept into a polished, 60-second conversational script, focusing on style and pacing ready for text-to-speech conversion. Both agent steps utilize memory buffer n8n nodes for conversational context, although primarily used here for data transfer.


3. Audio Conversion: The final script text is sent to the Eleven Labs Text-to-Speech n8n node, which is configured as an HTTP Request. This n8n node converts the text into a binary MP3 file.


4. Delivery: The generated MP3 audio file is then handled by the final Send a message n8n node (Gmail). This step automatically attaches the audio file and emails it to a specified recipient, completing the fully automated n8n workflow from input to audio delivery.

To deploy and utilize this powerful n8n workflow, follow these steps:

1. Import: Copy the provided n8n workflow JSON and paste it into your n8n instance using the 'New' -> 'Import from JSON' option.


2. Credentials Setup: This n8n template requires four key credentials:

1. Customize: In the Eleven Labs Text-to-Speech n8n node, update YOURVOICEID in the URL to select your preferred voice.


2. Activation: Once all credentials and settings are updated, activate the n8n trigger and the entire n8n workflow is ready to run.

When chat message received (LangChain Chat Trigger): Acts as the starting n8n trigger for the entire automation. It listens for user input (the podcast topic) to kick off the n8n workflow.
Podcast Idea/Topic Agent (LangChain Agent): This n8n node uses a detailed system prompt to transform the seed topic into a structured podcast idea. It relies on the OpenAI Chat Model to fulfill its role.
Podcast Script Agent (LangChain Agent): Takes the generated idea and executes a complex prompt (modeled after high-impact solo podcasts) to produce a 60-second script, ensuring it's ready for text-to-speech. It utilizes the Anthropic Chat Model n8n node.
Eleven Labs Text-to-Speech (HTTP Request n8n node): Essential for converting the script text into binary audio data. Key configuration includes using POST method, providing the Eleven Labs API key in the headers, and passing the text output of the previous n8n node in the body.

• Send a message (Gmail n8n node): The final action n8n node. It sends the audio file generated by Eleven Labs as an attachment to a specified email address, concluding the n8n workflow.