Quick overview
This workflow receives a webhook with a Base64-encoded WhatsApp call recording from a Google App Script, transcribes the audio using Groq’s Whisper API, and saves the formatted transcript as a text file to Google Drive via a Google Apps Script web app.
How it works
- Receives an HTTP POST webhook containing Base64 audio data plus optional metadata like filename, MIME type, and Google Drive links.
- Converts the Base64 payload into a binary audio file and generates a transcript filename based on the original audio name.
- Uploads the audio to Groq’s Whisper transcription endpoint (whisper-large-v3-turbo) and receives the transcript text.
- Sends the transcript and call metadata to a Google Apps Script web app that writes the transcript into a text file in a specified Google Drive folder.
Setup
- Create a Groq API key and add it as an HTTP Header Auth credential (Bearer token) for the transcription request.
- Deploy a Google Apps Script web app that supports the save_transcript action and can write files to your Google Drive.
- Update the Google Apps Script web app URL and target Google Drive folder ID used when saving the transcript.
- Copy the webhook URL for the “whatsapp-audio” endpoint and configure your WhatsApp/audio capture process to POST the required fields (fileData, fileName, mimeType, and optional Drive link metadata).
Requirements
- You need to create a Google App Script from your google drive account.
Additional info
Use this GOOGLE APP SCRIPT AND REPLACE THE TWO VARIABLES - AUDIO_FOLDER_ID, N8N_WEBHOOK_URL
You can find the App Script from this github repo - https://github.com/Progressive-Programmer/whatsapp-n8n-google-app-script.git