Transcribe your Google Drive files
Sync a Google Drive folder into Breyta so audio and video are transcribed automatically and documents, spreadsheets, PDFs, and other files are saved in a private Synced Drive files folder with their original names after you share the folder with google-drive-sync@breyta.iam.gserviceaccount.com and give Editor access for video files.
Created by Chris Moen • Version 81 • 21 steps
What you get
- Sync a Google Drive folder into Breyta so audio and video are transcribed automatically and documents, spreadsheets, PDFs, and other files are saved in a private Synced Drive files folder with their original names after you share the folder with google-drive-sync@breyta.iam.gserviceaccount.com and give Editor access for video files.
Integrations
- assemblyai
- google-drive-service-account
- synced-drive-files
- Google Drive
- Breyta Resources
How it works
- Normalize manual transcription ids
- Resolve first sync lookback window
- Load last sync state
- Load pending AssemblyAI transcriptions
- Select pending transcriptions to reconcile
- Collect file ids already queued for transcription
- List recent AssemblyAI transcriptions
- Index pending transcript summaries
- List files in Google Drive folder
- Pause before next page
- Select oldest file batch for this run
- Plan non-media file sync items for this batch
- Select audio and video files in this batch
- Classify recording files for transcription
- Plan media downloads for transcription
- Summarize recording processing
- Summarize transcript reconciliation
- Save pending AssemblyAI transcriptions
- Build Drive file metadata records for this batch
- Build next sync state
- Save last sync state
What This Does
This flow keeps a Google Drive folder in sync with Breyta.
- Audio and video files are automatically transcribed.
- Google Docs, Google Sheets, PDFs, slides, chats, and other non-media files are saved in Breyta.
- Synced files keep their original file names.
- Saved non-media files go into a private Breyta storage folder labeled
Synced Drive files.
Before You Start
- Copy the Google Drive folder link you want to sync.
- In Google Drive, share that folder with
google-drive-sync@breyta.iam.gserviceaccount.com. - If the folder contains video files, give the service account Editor access.
What You Set Up
During setup, you will:
- Paste the Google Drive folder link.
- Choose how far back the first sync should look.
If you do not change it, the first sync looks back 30 days.
Start Right Away
After setup, click Run first sync now in the UI if you want the first sync to start immediately. Otherwise, the flow will wait for the next hourly sync.
Good To Know
After the first sync, the flow keeps going from where it left off. Google-native files such as Docs and Sheets are exported into a standard file format when they are saved in Breyta.
FAQ
How do I transcribe Google Drive audio and video files automatically?
This app automatically syncs your Google Drive folder with Breyta to transcribe audio and video files while organising documents, spreadsheets, and PDFs into a private synced folder. It keeps your original filenames intact so you can find your data easily.
Which integrations does the Google Drive transcription workflow use?
The workflow uses AssemblyAI to process speech-to-text for media files and connects to Google Drive via a service account. Breyta manages the sync state through an internal Key Value store to ensure no files are missed or processed twice.
What is the setup process for syncing my Google Drive folder?
Share your target Google Drive folder with google-drive-sync@breyta.iam.gserviceaccount.com and grant Editor access. The app then scans the folder, identifies new media, and queues it for transcription based on your sync settings.
How does the app handle large volumes of files in Google Drive?
The app runs in batches to process the oldest files first and maintains a sync state to track progress. It checks for pending transcriptions, reconciles them with Google Drive metadata, and saves the final records in a dedicated folder.