Kani TTS is an educational demonstration of state-of-the-art AI video generation, making advanced technology accessible for learning, research, and creative exploration.
At Kani TTS, our mission is to showcase the possibilities of text-to-speech generation. We aim to empower students, educators, and enthusiasts to experiment with and understand the latest advancements in generative AI, all within a safe and accessible environment.
We believe in open research, transparency, and responsible AI. Kani TTS is not a commercial product, but a platform for learning and inspiration.
Kani TTS is built on top of open-source research, including the Juan 2.1 model and other community-driven AI projects. We have adapted and optimized these models to demonstrate real-time video and speech generation capabilities.
Our platform is designed for experimentation and learning. Users can explore how text prompts are transformed into video and audio, gaining insight into the inner workings of modern generative AI.
We support open research and the responsible advancement of AI for the benefit of all.
Making advanced AI accessible and understandable for learners and educators everywhere.
Fostering collaboration and sharing knowledge within the AI and creative technology communities.
Kani TTS is the result of collaborative efforts in AI research and engineering. By leveraging open-source models and contributing improvements back to the community, we hope to accelerate the pace of innovation in generative video and speech.
Have questions about Kani TTS, want to collaborate, or need support? We're happy to connect.
Contact Uskanitts.com is not an official website. This website is an independent overview of KaniTTS, an open-source project licensed under the Apache License 2.0. All trademarks and model rights belong to their respective owners. The original project is available on GitHub.