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.
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.
Stars
10
Forks
2
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model