Chinny is a new voice cloning app available on iOS and macOS that allows users to create voice clones entirely offline, ensuring privacy and security as no data leaves the device. Powered by the advanced AI model Chatterbox, Chinny requires no ads, registration, or network connectivity, and it is free to use with no hidden fees or usage restrictions. Users can leverage this app for various purposes, such as creating personalized audiobooks, voiceovers, or accessible read-alouds, all while maintaining complete control over their data. The app requires 3 GB of RAM and 3.41 GB of storage, and users must provide a clean voice sample for cloning. This matters because it offers a private and accessible way to utilize AI voice technology without compromising user data.
Sopro is a compact text-to-speech model with 169 million parameters, designed for real-time applications and capable of zero-shot voice cloning. It supports streaming and can generate 30 seconds of audio in just 7.5 seconds on a CPU, requiring only 3-12 seconds of reference audio for effective voice cloning. While it is not state-of-the-art and occasionally struggles with voice likeness, Sopro is a notable achievement given its development on a single L40S GPU and limited resources. The model is available under the Apache 2.0 license, although it currently supports only English due to data constraints.