Automatic Audio Transcription and Logging from Google Drive to Sheets - n8n Workflow

• Content teams and podcasters needing rapid transcription services.


• Researchers who frequently handle recorded interviews or meeting notes.


• Business users looking to leverage cloud services like AWS Transcribe within an automated n8n solution.


• Developers searching for reliable n8n templates integrating AWS, Google Drive, and Google Sheets.

Manually transcribing audio is time-consuming and prone to errors. This n8n workflow solves this by providing a hands-off, highly efficient automation pipeline. When an audio file is dropped into a monitored Google Drive folder, the automation immediately springs into action. It secures the file in AWS S3, initiates the powerful AWS Transcribe service, and uses the built-in n8n wait functionality to handle the asynchronous transcription process. Once complete, the transcript is retrieved and cleanly logged, alongside critical metadata, into a Google Sheet. This makes it an essential n8n templates solution for anyone handling high volumes of audio data, demonstrating the flexibility of the n8n node connections across multiple cloud platforms.

This automation follows a clear, step-by-step process orchestrated by the core n8n node flow:

1. Trigger Activation: The process begins with the Google Drive Trigger n8n trigger, activating instantly when a new file is uploaded to the designated Google Drive folder.


2. S3 Upload: The file is immediately uploaded to a specified AWS S3 bucket using the AWS S3 n8n node (AWS S3 1). This is required for AWS Transcribe input.


3. Transcription Initiation: The AWS Transcribe n8n node (AWS Transcribe 1) starts the transcription job, providing the S3 URI path derived from the previous steps.


4. Asynchronous Wait: Since transcription is an asynchronous, long-running task, the flow hits the Wait n8n node. This holds the workflow execution until a later action (resumption via a webhook, or subsequent monitoring step) signals the job's completion.


5. Result Retrieval: Upon resumption, the AWS Transcribe n8n node (AWS Transcribe 2) checks the status of the job using the get operation and retrieves the final transcript text.


6. Data Structuring: A Set n8n node cleans and structures the relevant data points: the file name, the original Google Drive link, the job creation time, and the complete transcript.


7. Logging to Sheets: Finally, the structured data is appended as a new row to the configured Google Sheets document using the Google Sheets n8n node, completing the end-to-end n8n workflow.

To deploy this comprehensive n8n workflow, follow these setup steps:

1. Import: Copy the provided n8n workflow JSON and import it directly into your n8n instance.


2. Google Drive Trigger: Configure the 'Google Drive Trigger1' n8n node. Select your existing Google Drive OAuth2 credential and specify the exact URL or ID of the folder you wish to monitor for new audio files.


3. AWS Credentials: Set up the required AWS credentials for S3 and Transcribe access. Apply these credentials to the 'AWS S3 1', 'AWS S3 2', 'AWS Transcribe 1', and 'AWS Transcribe 2' n8n nodes.


4. AWS S3 Configuration: In the 'AWS S3 1' n8n node, set the target bucketName where the audio files will be temporarily stored.


5. Google Sheets Setup: Configure the 'Google Sheets' n8n node. Select your Google Sheets OAuth2 credential, and replace the placeholder sheetId and ensure the range (A:D) matches the columns where you want to log the transcription data.


6. Activate: Save the n8n workflow and set the Google Drive n8n trigger to active. Ensure your n8n instance can handle webhook callbacks for the 'Wait' node resumption.

Google Drive Trigger1 (n8n trigger):
Function: Starts the n8n workflow upon detecting a new file creation.
Key Configuration: Triggers on 'fileCreated' in a 'specificFolder' defined by a folder URL/ID.
AWS S3 1 (n8n node):
Function: Uploads the incoming Google Drive file content to an AWS S3 bucket.
Key Configuration: operation: upload; bucketName: mybucket; fileName: set dynamically via expression ={{$json["name"]}}.
AWS Transcribe 1 (n8n node):
Function: Initiates the transcription job.
Key Configuration: operation: start; mediaFileUri: built dynamically to point to the S3 location: =s3://{{$node["AWS S3 2"].parameter["bucketName"]}}/{{$json["Key"]}}; transcriptionJobName: dynamic file name.
Wait (n8n node):
Function: Pauses the n8n workflow until the long-running AWS Transcribe job is completed and signals resume via a webhook.
Key Configuration: resume: webhook; webhookId: 12345.
AWS Transcribe 2 (n8n node):
Function: Retrieves the finalized transcription results once the job is complete.
Key Configuration: operation: get; transcriptionJobName: dynamic job name.
Set (n8n node):
Function: Maps and standardizes the data fields (creation time, recording name, transcription text) extracted from the AWS Transcribe output.
Google Sheets (n8n node):
Function: Appends the structured transcription data into the target spreadsheet.
Key Configuration: operation: append; range: A:D; Uses specific sheetId ('qwertz').