n8n Webhook Text to Speech: Generate Audio with OpenAI

Turn Webhook Text Into Speech—Instantly

This n8n workflow listens for text via a webhook, uses the OpenAI API to generate audio (text-to-speech), and returns the generated speech back through the webhook response—so you can automate voice output with minimal manual effort.

What this workflow does

• Receives a text input via a webhook when an external system sends a request to your n8n endpoint.
• Converts the received text to audio using OpenAI, using your configured OpenAI credentials.
• Sends the generated speech back by using a respond to webhook node, returning the audio as the webhook response.

Use cases

• Customer support automation: Convert incoming message text into spoken audio for agents or automated announcements.
• Content creation: Turn scripts or captions into voice audio on demand from any system that can call a webhook.
• Developer tooling: Build a simple text-to-speech API experience for your app by wiring requests to n8n.

Technical details

• Trigger: webhook (receives text input)
• OpenAI processing: n8n-nodes-langchain-openai (OpenAI API for text-to-speech generation)
• Response handling: respond to webhook (returns the generated audio through the webhook response)
• Includes: a sticky note for workflow guidance

Setup (quick steps)

1. Get your OpenAI API key from OpenAI.
2. Set up the webhook URL and parameters for the incoming text request.
3. Configure the OpenAI node using Create New Credentials.
4. Ensure the respond to webhook node is set to return the generated speech.

Perfect for n8n users, automation engineers, and SaaS operators who need reliable webhook-based text-to-speech automation with OpenAI.