Multi Format Vocal Output Generation

via “vocoder-agnostic mel-spectrogram generation with multiple vocoder backends”

text-to-speech model by undefined. 6,61,227 downloads.

Unique: Decouples mel-spectrogram generation from vocoding, enabling vocoder swapping without model retraining; includes built-in adapters for HiFi-GAN, UnivNet, and Vocos with automatic format conversion and normalization

vs others: More flexible than end-to-end models like Bark (which bundle vocoding) and enables faster iteration on vocoder improvements without retraining the TTS model