n8n Workflow: Speech-to-Text Webhook with Palatine Speech API

Turn Speech into Text via an n8n Webhook (Palatine Speech)

Send an audio file to a simple POST /transcribe webhook and get an instant speech-to-text transcription back as JSON—powered by Palatine Speech.

What this workflow does

This n8n automation exposes an HTTP endpoint that continuously stays available while the workflow is active, so external systems can call it repeatedly.

• Receives audio uploads using multipart/form-data in a POST request.
• Transcribes with Palatine Speech by forwarding the uploaded file to the Palatine Speech API.
• Uses palatine_large_highspeed and auto-detects spoken language.
• Returns the transcription to the caller as a JSON response.
• Keeps the endpoint live as long as the workflow remains active.

Use cases

• Media processing for SaaS: accept user voice notes and immediately return transcripts in your backend.
• Customer support tooling: convert inbound call recordings or support recordings to searchable text.
• Voice-to-doc automation: trigger transcription from your app and continue processing downstream (summaries, indexing, etc.).
• Engineering test harness: validate speech-to-text behavior with a stable webhook interface.

Technical details

• Nodes / components: webhook, respond to webhook, n8n-nodes-palatine-speech (Palatine Speech community node), plus supporting elements (e.g., sticky note).
• API integration: requires Palatine Speech API credentials (API key from the Palatine Speech dashboard).
• Transcription behavior: palatine_large_highspeed + automatic language detection.
• Activation: copy the webhook URL for the /transcribe endpoint and start using it after activation.

Setup highlights

• Install the Palatine Speech community node in n8n and add your credentials.
• Use the provided webhook URL for /transcribe and configure your client to POST the audio file.
• Optional: add webhook authentication (header check) and adjust the model settings for your latency/quality needs.