Operations & Systems
Google Drive to AI Speech-to-Text to Summary and Reporting
This workflow transcribes audio files from Google Drive using OpenAI, then summarizes the transcript into JSON and Markdown reports, saving them back to Drive. It notifies the user via Gmail and Telegram, with optional human approval.
Built · ~5.5 hours saved per week
Anyone needing automated transcription, summarization, and reporting of audio files.
This workflow watches a Google Drive folder for new audio files. When it finds one, it asks for approval. If approved, it transcribes the audio using OpenAI, summarizes it into JSON and Markdown reports, saves these reports to Google Drive, and then notifies users via email and Telegram with links to the reports.
Connect your Google Drive, Gmail, OpenAI, and Telegram accounts. Specify the Google Drive folder to monitor and the email/Telegram recipients in environment variables.
Google Drive account, Gmail account, OpenAI API key, Telegram account and bot, n8n instance.
You can change the approved file types, the summarization prompts, report formats, and notification methods.
Key Technologies: Google Drive,OpenAI (Whisper and GPT-4o-mini),Gmail,Telegram,n8n
Automation Value: Automatically transcribes audio, summarizes content, and generates reports. Simplifies information extraction from audio recordings. Ensures key insights are shared efficiently to relevant stakeholders. Maintains a human-in-the-loop for approval before processing.
Best Practices: Implement human approval for critical steps, especially before AI processing, to ensure control and accuracy. Use clear and specific prompts for AI models to achieve desired output formats and content. In this workflow, the detailed prompts for JSON and Markdown summarization ensure consistent and high-quality reports. Store both raw and processed data (raw transcript, JSON summary, Markdown report) for audit trails and future analysis. Utilize both email and chat notifications (Gmail and Telegram) to ensure broad and timely communication of results. Properly configure environment variables for sensitive data like API keys and recipient addresses for easier maintenance and security. Filter and limit data early in the workflow to minimize unnecessary processing and API calls.
Tags: Audio/Music/Voice, Data Transformation, AI Automation, Google, Telegram, OpenAI
Integrations: Email, OpenAI, Google Drive, Telegram