n8n Telegram Bot: Transcribe Voice Notes with Palatine Speech

Turn Telegram voice notes into text—automatically

This n8n workflow listens to your Telegram bot messages, transcribes incoming voice notes using Palatine Speech, and replies in the same chat with the transcript. If the message is text instead of audio, it simply echoes the text back unchanged.

What this workflow does

• Triggers on new Telegram messages using the Telegram Trigger node.
• Detects the message type (voice note vs. text) with a Switch step.
• Downloads the voice file from Telegram when a voice note is received.
• Sends the audio to Palatine Speech to generate a transcription.
• Replies in the same Telegram chat with the transcription text.
• Echoes text messages unchanged by replying back with the same text content.

Use cases

• Hands-free note-taking: capture quick voice notes in Telegram and receive a written transcript instantly.
• Support triage: transcribe customer voice messages to speed up understanding and follow-up.
• Team updates: convert spoken updates from a Telegram channel/group into text for easier reading.

Technical details

• Telegram Trigger to detect new bot messages.
• Switch to branch logic between voice notes and text messages.
• Telegram node to download voice files and send replies.
• Palatine Speech community node (n8n-nodes-palatine-speechpalatine speech) to transcribe audio.
• Uses supporting canvas elements like a Sticky Note for workflow clarity.

Setup requirements

• Install the Palatine Speech community node in n8n.
• Add Telegram Bot API credentials (bot token from BotFather) and connect them to the Telegram trigger and reply/download steps.
• Add Palatine Speech API credentials (API key from the Palatine Speech dashboard).

Designed for n8n users, automation engineers, and SaaS operators who want a reliable Telegram-to-text transcription workflow powered by Palatine Speech.