#TTS models

FACodec is an integral part of NaturalSpeech 3, transforming speech synthesis by efficiently converting speech waveforms into separate subspaces including content, prosody, timbre, and acoustic details. By using attribute factorization, it aids in the precise modeling and reconstruction of speech waveforms. FACodec enables the creation of both non-autoregressive and autoregressive TTS models, supporting zero-shot voice conversion. It is suitable for 16KHz audio and generates multiple speech codes, enhancing projects like VALL-E and contributing significantly to advancements in TTS research.

A comprehensive resource for tracking and showcasing open-access TTS models, it aids researchers, developers, and enthusiasts in staying updated with the latest advancements. This platform enhances the accessibility and awareness of various TTS models, featuring capabilities like multilingual options, emotional control, and longform synthesis. By compiling open-source TTS projects, it promotes contributions and provides insights into each model's licensing, documentation, and demonstrations, ensuring up-to-date engagement with cutting-edge developments.