Transcribe your Google Drive files

Sync a Google Drive folder to Breyta to automatically transcribe audio and video with AssemblyAI and save all files to a private Synced Drive files folder.

Created by Chris Moen • Version 81 • 21 steps

Automate your media transcription workflow

Manually transcribing audio and video files is a slow process that pulls your team away from more important tasks. This workflow connects your Google Drive directly to AssemblyAI, ensuring every recording you save is automatically converted into text. By syncing a specific folder to Breyta, you create a self-managing system that handles file intake, processing, and storage without any manual oversight. All completed files are safely stored in a private folder, keeping your workspace organised and your data secure.

How the sync process works

The workflow operates on a smart polling system that periodically checks your Google Drive for new activity. It begins by looking at your previous sync state to identify only the most recent files, preventing duplicate transcriptions. The logic then filters your folder content into two groups: standard documents and media files.

For media files, the system initiates a request with AssemblyAI and tracks the status in a Key-Value store. This allows the flow to manage long-running transcription tasks by pausing and resuming as needed. It handles file batching to stay within rate limits and ensures that even if you upload twenty videos at once, they are processed reliably. Once the transcription is ready, the metadata is updated, and the final records are saved for your team to access.

Key features and benefits

Using this template helps you maintain a searchable archive of all spoken content without lifting a finger. It is particularly useful for teams handling interviews, meeting recordings, or video production.

  • Automatic discovery: Automatically detects new audio and video files as soon as they hit your Google Drive folder.
  • Smart state management: Remembers where it left off so you never pay to transcribe the same file twice.
  • Media classification: Intelligently distinguishes between media that needs transcribing and other files that just need syncing.
  • Private storage: Saves all processed data to a secure, synced drive folder for consistent file organisation.
  • Scalable processing: Uses batching and wait steps to handle large volumes of content without errors.

Integrated tools

This workflow combines the storage reliability of Google Drive with the precise speech-to-text capabilities of AssemblyAI. By using Breyta as the logic engine, you bridge the gap between file storage and artificial intelligence, creating a dependable pipeline for your media assets.

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

What does the Google Drive transcription workflow do?

This automation monitors a specific Google Drive folder, identifies new audio or video files, and automatically transcribes them using AssemblyAI. It then saves the synced files and transcripts into a private folder within your Synced Drive files.

Which services are required for this transcription sync?

The process uses AssemblyAI for high-quality speech-to-text conversion and Google Drive for file storage. It also uses Breyta’s internal Key Value storage to keep track of your sync state and pending transcription jobs.

How does the automation handle large numbers of media files?

The flow lists files in your chosen folder and filters for media formats like audio and video. It handles files in batches, tracks the status of pending transcripts, and saves the final metadata so you don't process the same file twice.

How do I set up the transcription sync for my folders?

You'll need to connect your Google Drive and AssemblyAI accounts, then select the specific folder you want to monitor. The workflow includes a customisable lookback window to decide how many historical files it should process during the first run.