Transcribe your Google Drive files

Sync a Google Drive folder to Breyta for automatic audio/video transcription. Files are saved in a private Synced Drive files folder with original names.

Created by Chris Moen • Version 81 • 21 steps

Automatically transcribe your media library

This workflow automates the time-consuming task of converting audio and video files into text. By connecting your Google Drive folder to Breyta, every new recording you upload is automatically detected, processed, and transcribed. The flow organises everything within a private Synced Drive files folder, ensuring your transcripts are easy to find and share with your team.

How the automation works

The process begins by checking your Google Drive for new activity. It uses a Key-Value (KV) store to remember where it left off, so it only processes new or updated files. The system filters your folder for supported audio and video formats while ignoring non-media files.

Once the media is identified, the flow integrates with AssemblyAI to handle the transcription. It manages the queue by checking the status of pending transcriptions and reconciling them with your file metadata. The workflow is designed to handle batches of files, using a built-in wait step to manage rate limits and ensure consistent performance. Finally, it saves the updated sync state and stores the completed transcript summaries, keeping your records accurate without any manual input.

Key benefits for your team

Manually transcribing interviews, meetings, or field recordings is a drain on resources. This template eliminates that overhead so you can focus on analysing the content rather than typing it out.

  • Centralised storage: Keep all your transcripts in one secure, private folder with original filenames for easy searching.
  • Smart filtering: The flow automatically distinguishes between media files and documents, only sending relevant data for transcription.
  • State management: By tracking the last sync state, the automation ensures no file is missed and no data is processed twice.
  • Customisable intervals: You can control the lookback window and batch sizes to suit your team's specific volume of work.

Reliable media processing

We have built this workflow to be resilient. It handles the technical heavy lifting, including classifying recording files, managing HTTP requests to AssemblyAI, and building detailed metadata records. Whether you are managing a few weekly recordings or a large volume of research data, this template provides a steady, automated pipeline for all your transcription needs.

Steps

  1. Normalize manual transcription ids (function)
  2. Resolve first sync lookback window (function)
  3. Load last sync state (kv)
  4. Load pending AssemblyAI transcriptions (kv)
  5. Select pending transcriptions to reconcile (function)
  6. Collect file ids already queued for transcription (function)
  7. List recent AssemblyAI transcriptions (http)
  8. Index pending transcript summaries (function)
  9. List files in Google Drive folder (http)
  10. Pause before next page (wait)
  11. Select oldest file batch for this run (function)
  12. Plan non-media file sync items for this batch (function)
  13. Select audio and video files in this batch (function)
  14. Classify recording files for transcription (function)
  15. Plan media downloads for transcription (function)
  16. Summarize recording processing (function)
  17. Summarize transcript reconciliation (function)
  18. Save pending AssemblyAI transcriptions (kv)
  19. Build Drive file metadata records for this batch (function)
  20. Build next sync state (function)
  21. Save last sync state (kv)

FAQ

How do I automate transcription for files in Google Drive?

This workflow automatically monitors a specific Google Drive folder for new audio and video files. When you add a file, Breyta sends it for transcription and saves the result in your private Synced Drive files folder.

Which services does this transcription workflow use?

The automation uses Google Drive to source your files, AssemblyAI to generate the transcripts, and Breyta's internal storage to keep track of your sync state. It processes files in batches to ensure every recording is handled reliably.

How does Breyta track which files have been transcribed?

The flow identifies audio and video formats, then checks if they have already been processed by looking at your sync history. It manages pending transcriptions and reconciles them once they're ready, so you don't have to manually check the status.

What is required to set up this Google Drive transcription sync?

You'll need to connect your Google Drive account and provide an AssemblyAI key. Once connected, you can choose the specific folder you want to monitor, and the workflow will begin syncing your files automatically.