ParsVoice

First Persian Zero-Shot Text-to-Speech Model
High-quality Persian speech synthesis with natural speaker similarity

Reference

ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis (2025)
Mohammad Javad Ranjbar, Azadeh Shakery, Heshaam Faili
University of Tehran

Sample Demonstrations

Listen to high-quality synthesized speech samples generated by our zero-shot TTS model

Loading samples...