Skip to content

Trainer MVP: Course DB Builder

This workflow scans Google Drive folders to discover audio/video content, transcribes voice recordings, and structures the results in a database for easy querying. It's designed to help trainers and educators build searchable knowledge bases from their existing course materials.

Purpose

No business context provided yet — add a context.md to enrich this documentation.

Based on the workflow description, this automation serves trainers who have accumulated course content across Google Drive folders and need to make that content searchable and accessible. The workflow transforms scattered audio/video files into a structured database that can be queried for specific topics, making course content discovery much more efficient.

How It Works

  1. Manual Trigger: The workflow starts when manually executed
  2. Google Drive Scan: Connects to Google Drive and scans the root folder for content
  3. Content Discovery: Identifies folders and files that contain course materials
  4. Voice Transcription: (Planned) Processes audio/video files to extract text content
  5. Database Storage: (Planned) Structures transcribed content in a queryable database

Note: This workflow appears to be in early development with only the Google Drive connection implemented.

Mermaid Diagram

graph TD
    A[Manual Trigger] --> B[Google Drive - List Folders]
    B --> C[Process Content - Planned]
    C --> D[Transcribe Audio - Planned]
    D --> E[Store in Database - Planned]

Trigger

Manual Trigger: The workflow runs when you click "Test workflow" or execute it manually. This gives you control over when the content scanning and processing occurs.

Nodes Used

Node Type Purpose
Manual Trigger Starts the workflow on demand
Google Drive Lists folders and files from Google Drive root directory
Sticky Note Documents the workflow's purpose and scope

External Services & Credentials Required

Google Drive

  • Service: Google Drive API
  • Credential Type: OAuth2
  • Required Permissions:
    • Read access to Google Drive files and folders
    • Ability to list directory contents
  • Setup: Configure Google Drive OAuth2 credentials in n8n

Additional Services (Planned)

  • Transcription Service: Will need speech-to-text API (e.g., OpenAI Whisper, Google Speech-to-Text)
  • Database: Will require database credentials for storing structured content

Environment Variables

Currently no environment variables are required. Future iterations may need: - Database connection strings - API keys for transcription services - File processing limits or batch sizes

Data Flow

Input

  • Google Drive folder structure starting from root directory
  • Audio/video files within discovered folders (planned)

Output

  • List of folders and files from Google Drive
  • Transcribed text content (planned)
  • Structured database records (planned)

Current Data Structure

The Google Drive node returns folder information including: - Folder names and IDs - File metadata - Folder hierarchy

Error Handling

No explicit error handling is currently implemented. Consider adding: - Retry logic for Google Drive API calls - Error notifications for failed transcriptions - Validation for supported file formats - Handling of rate limits and quota restrictions

Known Limitations

  • Workflow is in early development stage with only Google Drive integration complete
  • No transcription functionality implemented yet
  • No database storage configured
  • Limited to root folder scanning (no recursive folder traversal visible)
  • No file type filtering or validation

No related workflows identified in the current context.

Setup Instructions

  1. Import Workflow

    • Copy the workflow JSON
    • Import into your n8n instance

  2. Configure Google Drive Credentials

    • Go to n8n Credentials
    • Create new Google Drive OAuth2 credential
    • Complete OAuth flow with Google
    • Assign credential to the Google Drive node

  3. Test Basic Functionality

    • Click "Test workflow" to verify Google Drive connection
    • Check that folders are being listed correctly

  4. Future Development

    • Add transcription service integration
    • Configure database connection
    • Implement file processing logic
    • Add error handling and validation

  5. Production Considerations

    • Set up proper error notifications
    • Configure appropriate execution limits
    • Consider scheduling for automatic updates
    • Implement proper logging for debugging