# Multi-emotional speech synthesis

Orpheus is a high-performance text-to-speech model, fine-tuned specifically for natural emotional speech synthesis. This repository hosts the 8-bit quantized version of the 3-billion-parameter model, optimizing efficiency while maintaining high-quality output.

Bengali text-to-speech model based on Orpheus architecture, supporting multiple emotional styles

Bark is a Transformer-based multilingual text-to-audio model developed by Suno, capable of generating realistic speech, music, and non-verbal sounds