This n8n workflow automates the process of converting text scripts stored in Google Drive into audio files, suitable for voice narration or multimedia projects. It is designed for users who want a fully automated pipeline that retrieves scripts, synthesizes speech using a custom Python script, and uploads the resulting audio back to Google Drive.

The workflow begins with an external trigger, which could be an API call or event, passing in folder IDs for scripts and audio storage. It then aggregates these inputs to process multiple scripts in batch mode. Using the Google Drive node, it fetches the list of script files from a specified folder.

Each script is processed in a loop: the script file is downloaded from Google Drive, saved temporarily on the local system, and then fed into a Python-based voice synthesis script that generates a WAV audio file. This audio file is then read and uploaded back to a designated Google Drive folder for storage or further use.

A helpful sticky note node provides instructions and details about the workflow, emphasizing the need for plain text scripts with a .txt extension and the deployment of the custom voice generation script at a specific path.

This automated setup is ideal for content creators, educators, or developers who need to generate audio versions of text scripts regularly, leveraging cloud storage and custom voice synthesis models for scalable, batch processing.

Node Count	11 – 20 Nodes
Nodes Used	aggregate, executeCommand, executeWorkflowTrigger, googleDrive, manualTrigger, readWriteFile, set, splitInBatches, stickyNote