Expose a speech-to-text /transcribe API with Palatine Speech

Description

Quick overview
This workflow exposes a POST /transcribe webhook that accepts an uploaded audio file and uses Palatine Speech to generate a transcript, returning the transcription result as a JSON response.

How it works
Receives a POST request with an audio file sent as multipart/form-data.
Passes the uploaded file to Palatine Speech for transcription.
Palatine Speech converts the audio to text using the palatine_large_highspeed model and detects the spoken language automatically.
Returns the transcription back to the caller as a JSON response.
The endpoint stays available while the workflow is active, so other systems can call it repeatedly.

Setup
Install the Palatine Speech community node: on the canvas press the + button, search for Palatine, open the node and click Install node. Then add your Palatine Speech API credentials in n8n.
Copy the webhook URL for the /transcribe endpoint and configure your client app to POST the audio file to it.
Activate the workflow and, if needed, adjust the Palatine Speech model setting to match your latency/quality needs.

Requirements
Palatine Speech API credentials (API key from the Palatine Speech dashboard)
Palatine Speech community node installed (works on n8n Cloud and self-hosted)

Customization
Add an authentication header check on the webhook before exposing it publicly
Return SRT or VTT subtitles instead of plain text
Store every transcript in a database or spreadsheet
Switch the model to palatine_small for faster processing