This n8n workflow automates the process of generating audio content using the notdaniel/voxtral-small-24b-2507 model from Replicate. It starts when a user clicks ‘execute’, retrieves and sets an API key, then creates a prediction request with input audio. The workflow polls for prediction status, waits for completion, and processes the final audio output. This setup is ideal for automating AI-driven audio content creation for podcasts, voiceovers, or creative projects. It integrates manual triggers, HTTP requests, scripting, and polling to ensure a seamless and automatic generation process.