Batch transcribe Google Drive videos to text files with Gemini

Description

Who’s it for

This workflow is designed for creators, researchers, and operators who need to transcribe large volumes of video content stored in Google Drive. It is especially useful for users working with TikTok archives, interview recordings, or social media datasets where manual transcription would be time-consuming and expensive.

How it works / What it does

This workflow automatically processes videos from a designated Google Drive folder, transcribes each file using Google Gemini, and saves the results as individual text files.

Each video is handled independently:

Videos are pulled from an “Incoming” folder
The file is downloaded and sent to Gemini for transcription
A .txt transcript file is created in a separate folder
The original video is moved to a “Processed” folder after success

This structure ensures progress is saved continuously, allowing the workflow to resume where it left off if interrupted.

How to set up
Create three Google Drive folders:
Incoming (source videos)
Processed (completed videos)
Transcripts (output files)
Add your folder IDs to the Config node
Connect your Google Drive and Gemini credentials
Run the workflow using the Manual Trigger (or Schedule Trigger for automation)

Requirements
n8n instance (cloud or self-hosted)
Google Drive API credentials
Google Gemini API access
Video files stored in Google Drive

How to customize the workflow
Adjust the transcription prompt in the Config node for different output styles
Modify the Wait node to control processing speed and avoid rate limits
Change file naming conventions in the formatting node
Add logging or notifications for failed transcriptions
Extend the workflow to combine transcripts into a single master document