Learn to rapidly develop a real-time voice-to-voice translator using open-source tools in this 29-minute hands-on workshop. Build an AI agent that processes speech-to-text, performs language translation, and synthesizes speech responses while optimizing for minimal latency. Master speech-to-text processing with open-source models, implement language translation using LLM-powered tools, and create speech synthesis capabilities for real-time responses. Discover techniques for optimizing latency to ensure seamless interaction and explore deployment strategies using open-source frameworks and APIs. Follow along with a live coding demonstration where you'll build alongside the instructor, with access to a provided GitHub repository for reproducible learning and further iteration.