Whisper Speech is a fully open-source text-to-speech model trained by Collabora and Lion on the Juwels supercomputer. It supports multiple languages and various input formats, including Node.js, Python, Elixir, HTTP, Cog, and Docker. The model's strength lies in its efficient speech synthesis and flexible deployment options. Price-wise, Whisper Speech is completely free. It is aimed at providing developers and researchers with a powerful and customizable text-to-speech solution.