MahtaFetrat/ManaTTS-Persian-Tacotron2-Model

Tacotron2 Persian Text-to-Speech Model trained on ManaTTS, the largest open single-speaker Persian speech dataset with over 114 hours of high-quality audio.

36
/ 100
Emerging

This project offers a Text-to-Speech (TTS) solution specifically for the Persian language, enabling you to convert written Persian text into natural-sounding spoken audio. You input Persian text, and it generates high-quality audio recordings of that text being read aloud. This is ideal for content creators, educators, or organizations looking to produce audio content in Persian.

No commits in the last 6 months.

Use this if you need to create clear, high-quality spoken audio from written Persian text, especially for applications like audiobooks, educational materials, or accessibility tools for the blind and visually impaired community.

Not ideal if you need to generate speech in a language other than Persian or require multiple distinct speaker voices, as this model focuses on a single, high-quality Persian voice.

Persian-content-creation audiobook-production accessibility-tools e-learning-Persian speech-synthesis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Jupyter Notebook

License

Last pushed

Jul 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/MahtaFetrat/ManaTTS-Persian-Tacotron2-Model"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.