Auto-Transcribe Telegram Voice Messages with Whisper & Google Workspace

This n8n workflow automates the transcription of voice messages sent to a Telegram bot. Upon receiving a message, it checks if it's a valid audio voice note. If so, it downloads the .oga file, transcribes it accurately using OpenAI's Whisper API, uploads the original audio to Google Drive for backup, merges the transcript with metadata like date, duration, and audio URL, then appends everything to a Google Sheet as structured logs. Finally, it sends a formatted reply to the user in Telegram with the transcript and download link. Non-audio messages receive a polite rejection.

Key benefits include hands-free conversion of voice memos into searchable text, eliminating manual transcription time, secure cloud backups, and organized data storage. It's highly efficient for high-volume voice inputs, with robust error handling for invalid files.

Ideal for journalists capturing interviews, content creators managing podcasts or notes, busy professionals logging ideas on-the-go, or teams needing quick audio-to-text workflows. Save hours weekly on transcription while gaining analytics-ready data in Sheets.

Setup is straightforward: Configure Telegram bot credentials, OpenAI API key, and Google Workspace auth. No coding required—activate and your bot is ready to transcribe instantly.