The F5-TTS is a new, fully non-autoregressive text-to-speech system based on Flow Matching with Diffusion Transformer (DiT). This innovative AI technology allows users to generate high-quality speech locally on their devices. The system is open source, free to use, and can clone voices with zero-shot capability. Users have demonstrated its versatility by generating speech in various famous voices, such as Peter Griffin, Donald Trump, and Scarlett Johansson's voice from the movie 'Her'. The F5-TTS can be easily installed and run using Python, making it accessible for a wide range of applications, including voice cloning and lip-syncing when combined with other tools like Dreamtalk and Pinokio. Additionally, the F5-TTS can be integrated with MLX for enhanced functionality.