keithito/tacotron
A TensorFlow implementation of Google's Tacotron neural text-to-speech model for synthesizing speech from text.
Not currently ranked — collecting fresh signals.
star history
This repository provides an open-source implementation of Google’s Tacotron architecture, a sequence-to-sequence model that generates speech audio directly from text. It includes training code, pre-trained models, and supports synthesis using the LJ Speech Dataset. The implementation uses TensorFlow and supports GPU acceleration for training and inference.
Frequently asked
- What is keithito/tacotron?
- A TensorFlow implementation of Google's Tacotron neural text-to-speech model for synthesizing speech from text.
- Is tacotron open source?
- Yes — keithito/tacotron is open source, released under the MIT license.
- What language is tacotron written in?
- keithito/tacotron is primarily written in Python.
- How popular is tacotron?
- keithito/tacotron has 3k stars on GitHub.
- Where can I find tacotron?
- keithito/tacotron is on GitHub at https://github.com/keithito/tacotron.