Automated Telegram Voice Note Transcription with Gemini AI
detail.loadingPreview
Automatically transcribe your Telegram voice notes and audio messages using Google Gemini's advanced AI. Receive instant text replies directly within your Telegram chat, streamlining communication and ensuring you never miss a detail from an audio message.
About This Workflow
Effortlessly convert your Telegram voice notes and audio files into readable text with this powerful n8n workflow. Leveraging the cutting-edge capabilities of Google Gemini, this automation listens for incoming audio messages on Telegram, securely uploads them to a specified storage, and then sends them for AI-powered transcription. The transcribed text is then sent directly back to your Telegram chat, providing a quick and efficient way to review spoken content without needing to listen to the audio. Perfect for busy professionals, students, or anyone who frequently receives voice messages and prefers text-based communication.
Key Features
- Telegram Integration: Seamlessly triggers on incoming voice notes and sends transcribed text replies.
- Gemini AI Transcription: Utilizes Google Gemini's powerful speech-to-text capabilities for accurate transcription.
- Automated File Handling: Manages the secure upload and processing of audio files to an external service for transcription.
- Smart Message Routing: Differentiates between text messages and audio files to ensure only relevant content is processed for transcription.
- Instant Text Replies: Delivers transcription results directly to your Telegram chat for immediate access.
How To Use
- Configure Telegram Trigger: Set up your
Telegram Trigger1node with your Telegram Bot Token. This node will listen for all incoming messages. - Setup Switch Node: Configure the
Switchnode to check for incoming audio messages. A common condition is to check if{{ $json.message.voice }}or{{ $json.message.audio }}exists. Route thetruepath toTelegram3(for transcription) and thefalsepath (for text messages) toText messages go this way. - Extract File from Telegram: Ensure the
Telegram3node (or a preceding node if needed) is configured to extract thefile_idfrom the incoming voice message and potentially download the audio file data. - Initialize Upload Session: Configure the
initialize upload sessionHTTP Request node. This will interact with your chosen file storage service (e.g., Google Cloud Storage, AWS S3) to prepare an upload, obtaining an upload URL or session ID. - Upload File: Set up the
Upload fileHTTP Request node to send the actual audio file (extracted from Telegram) to the storage service using the session details from the previous step. Ensure the file is attached correctly as binary data. - Ask Gemini to Transcribe: Configure the
Ask Gemini to transcribeHTTP Request node. Point it to the Google Gemini API endpoint for speech-to-text, providing your API key or authentication. Pass the URL or reference to the uploaded audio file from the previous step as the input for transcription. - Reply in Telegram: Finally, configure the
Reply in Telegramnode. Use an expression like{{ $json.data.transcriptionResult }}(adjust based on the actual Gemini API response structure) to embed the transcribed text and send it back to the originating Telegram chat.
Apps Used
Workflow JSON
{
"id": "9e6e5c9b-086c-41a7-8c3b-27e5298d7065",
"name": "Automated Telegram Voice Note Transcription with Gemini AI",
"nodes": 26,
"category": "Personal",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 9e6e5c9b-086c...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
Smart Expense Tracking with Telegram & AI
Automate your personal finance management by turning your Telegram chat into an intelligent expense tracker. Simply send a photo of a receipt or a text message, and this workflow uses AI to categorize your spending, extract crucial details, and provide instant summaries.
Send Obsidian Notes as Emails with Dynamic Attachments
This workflow empowers you to transform your Obsidian notes into dynamic emails, complete with custom metadata from YAML frontmatter and automated attachment handling. Seamlessly share your thoughts and files directly from your preferred note-taking environment.
Daily AI-Powered Morning Briefing
Start your day with clarity and focus using this n8n workflow. It automatically fetches your tasks from Todoist and events from Google Calendar, then leverages AI to create a concise, personalized daily briefing delivered directly to your inbox every morning. This ensures you always know your top priorities and upcoming schedule at a glance.