This workflow enables users to generate audio files from text inputs via a webhook. It is designed to be triggered by a POST request containing text, which is then sent to OpenAI’s API to convert the text into speech.
Here’s a step-by-step breakdown:
1. Webhook Trigger: The workflow starts with a webhook node that listens for incoming POST requests on the specified path (`generate_audio`). You can test this URL manually or set it up for production use.
2. Respond Node: After receiving the request, the workflow responds immediately to acknowledge receipt.
3. OpenAI Node: The text received in the POST request payload (`text_to_convert`) is sent to OpenAI’s API configured for audio resource generation. The voice used is set to “fable”.
4. Output: The workflow finally outputs the generated audio file as a binary response.
This setup is useful for scenarios where you want to convert user-submitted text into speech dynamically, such as creating audiobooks, voice alerts, or accessibility tools that read out content.
Additionally, there are sticky notes in the workflow providing configuration tips, such as testing the webhook URL and connecting OpenAI credentials properly.
Reviews
There are no reviews yet.