Released Models

English

TTS Models	Dataset	Commit	Audio Sample	Details
Tacotron-iter-62410	LJSpeech	99d56f7	link	First model with plain Tacotron implementation.
Tacotron-iter-170K	LJSpeech	e00bc66	link	More stable and longer trained model.
Tacotron-iter-270K	LJSpeech	256ed63	link	Stop-Token prediction is added, to detect end of speech.
Tacotron-iter-120K	LJSpeech	bf7590	link	Better for longer sentences
Tacotron-iter-108K	TWEB	2810d57	link	https://github.com/mozilla/TTS/issues/22
Tacotron-iter-185K	LJSpeech	branch	link	link
Tacotron2-iter-260K	LJSpeech	branch	soundcloud	Tacotron2 + WaveRNN (Mixture of Logistic Distributions)
Tacotron2	LJSpeech	branch	soon to come	details
Tacotron2 with Graves (soon)	LJSpeech	branch	soon to come	details

Speaker Encoder Models	Dataset	Commit
Speaker-Encoder-iter25k	LibriSpeech	...

Simple packaging - self contained package that runs an HTTP API for a pre-trained TTS model

How to use:

1. Create a fresh virtual environment with Python 3.6
2. $ apt-get install espeak libsndfile1
3. $ pip install python_package_url_from_table_below
4. $ python -m TTS.server.server
5. Open http://localhost:5002

Model	Dataset	Python package	nginx/uWSGI config files
Tacotron2-iter-260K	LJSpeech	TTS-0.0.1+b6b513f-py3-none-any.whl	t2-ljspeech-mold-nginx-uwsgi.zip

The server is a Flask application. For deployment with multiple workers see the nginx/uWSGI config files also linked in the table above.

German

Soon...

Portuguese

model details by @Edresson