AI Podcast Generation from Google Sheets (Multi-Speaker) - n8n Workflow

Content creators and marketers looking to rapidly produce high-quality podcast audio.
Users requiring custom AI-powered text-to-speech generation.
Developers needing advanced polling logic within an n8n workflow.
Teams that manage content scripts in Google Sheets.

Generating long-form, multi-speaker audio content with AI often requires managing asynchronous processes and polling an external API until the job is complete. This powerful n8n workflow solves this complexity by taking a structured podcast script directly from a Google Sheets document. It utilizes an external Text-to-Speech (TTS) service via an HTTP request, and crucially, implements a robust polling loop using the Wait and If n8n node configuration to ensure the audio is fully generated before attempting to download it. This specific n8n workflow is perfect for scaling content creation, allowing you to turn spreadsheet data into professional audio files automatically and store them securely in Google Drive. This is one of the most useful n8n templates for efficient audio production using n8n.

The process begins with the n8n trigger, which is a manual execution (When clicking ‘Test workflow’). 1. Data Extraction: The n8n workflow uses the Google Sheets n8n node (Get Podcast text) to read the structured script rows defining the speakers and dialogue. 2. Script Consolidation: The data is aggregated and processed by the Code n8n node (Full Podcast Text) to format the script correctly for the multi-speaker AI API’s required input structure. 3. Generation Request: An HTTP Request n8n node (Create Audio) initiates the audio generation job with the external TTS provider, receiving a job ID. 4. Asynchronous Polling Loop: The n8n workflow enters a waiting period (Wait 60 sec.). It then checks the job status (Get status). The Completed? If n8n node determines if the job is finished. If not, the n8n workflow loops back to the wait step, ensuring the process is resilient and handles typical AI generation latency. 5. Download & Storage: Once complete, the n8n workflow retrieves the audio file URL (Get Url Audio), downloads the file content (Get File Audio), and finally uploads the generated podcast audio file to Google Drive using the dedicated Google Drive n8n node (Upload Audio).

1. Import the n8n workflow JSON: In your n8n instance, navigate to the workflows section, click "+ New" -> "Import from JSON" and paste the provided code.


2. Google Sheets Credentials: Configure the Get Podcast text n8n node with your Google Sheets credentials. Specify the Sheet ID and the range containing your podcast script data.


3. Google Drive Credentials: Configure the Upload Audio n8n node with Google Drive credentials, specifying the target folder ID for the generated audio files.


4. API Configuration (HTTP Requests): The three HTTP Request n8n node instances (Create Audio, Get status, Get Url Audio) must be configured with the specific URL endpoints, authentication headers (API keys), and JSON body structures required by your chosen external AI text-to-speech service. These settings are crucial for this n8n workflow to function.


5. Code Node Customization: Review the Full Podcast Text Code n8n node to ensure the data transformation logic accurately prepares the Google Sheet data for the TTS API input format.


6. Testing: Execute the n8n trigger manually to ensure the entire n8n workflow runs successfully and handles the polling loop correctly.

When clicking ‘Test workflow’ (Manual Trigger n8n trigger): Serves as the starting point for testing and manual execution of this n8n workflow.
Get Podcast text (Google Sheets n8n node): Retrieves the structured script data, which details speaker lines, from a designated spreadsheet.
Full Podcast Text (Code n8n node): Uses custom JavaScript scripting to combine and transform the individual script rows from Google Sheets into the single, complex payload required by the multi-speaker AI generation API.
Create Audio (HTTP Request n8n node): Sends the prepared script to the AI service via API to initiate the text-to-audio generation process.
Wait 60 sec. (Wait n8n node): An essential element of the asynchronous polling mechanism, pausing the n8n workflow for a defined interval before checking status.
Completed? (If n8n node): This n8n node manages the control flow, routing the execution back to the Wait n8n node if the audio generation is not yet complete, or forward to download if it is.
Get File Audio (HTTP Request n8n node): Downloads the actual binary content of the newly generated podcast file using the temporary download URL.
Upload Audio (Google Drive n8n node): The final step, uploading the generated audio file to a specified Google Drive location for secure storage and distribution.