Kani-TTS-400M-UR

Sample Generated Audio

---

Kani-TTS-400M-UR is a Urdu Text-to-Speech (TTS) model based on Kani-TTS 400M. It has been trained on a high-quality Urdu speech dataset to produce natural, expressive, and human-like voice synthesis.

---

Model Overview

Attribute	Description
Base Model	Kani-TTS 400M
Language	Urdu 🇵🇰
Task	Text-to-Speech (TTS)
Model Size	~400M Parameters
Frameworks	PyTorch • Transformers

---

Inference

Try the model directly in Colab using the link below:

Run Inference on Google Colab

---

Acknowledgments

Kani-tts-400m-ur is under the apache-2.0 license. If you use this model in your work, please acknowledge the creators and consider referencing this model as follows:

@model{Kani-TTS-400M-UR,
title = {kani-tts-400m-ur},
author = {Mahwiz Khalil},
year = {2025},
publisher = {Hugging Face},
howpublished = {\url{https://huggingface.co/mahwizzzz/kani-tts-400m-ur/}},
}