Need Help: Transcribing Telegram Voice Messages with Google Gemini in n8n
Hi everyone,
I’m trying to create a workflow in n8n to transcribe voice messages from Telegram using Google Gemini, but I’m struggling with the implementation. I’ve attempted to set up an HTTP request, but I’m having difficulty figuring out the correct method to:
- Retrieve the voice file from Telegram
- Convert the file to a format Gemini can process
- Send the audio file to Gemini for transcription
- Receive and handle the transcription result
I’ve spent considerable time searching documentation and online resources, but haven’t found a clear solution. Has anyone successfully implemented this workflow? Would appreciate any guidance, code snippets, or advice on approaching this challenge.
Thanks in advance for any help!
Information on your n8n setup
- **n8n version:1.76.0 (Self Hosted)
- **Database :Default (SQLite)
- **Running n8n via: (Docker)
- **Operating system: (Ubuntu)