Automated AI Text Generation with n8n and IBM Granite Model

This n8n workflow automates the process of generating AI-based text using the IBM Granite speech model via the Replicate API. It starts with a manual trigger, allowing users to initiate the process as needed. The workflow sets up necessary API tokens and configures input parameters such as audio input, prompt, and generation settings. It then sends a prediction request to the API and periodically checks the prediction status, waiting for the process to complete. Once successful, it returns a structured response containing the generated text URL, prediction ID, and status, along with logging and error handling features. The setup is ideal for automating speech-to-text or text generation tasks in content creation, customer support automation, or any scenario requiring AI-generated text from audio inputs.