TTS is a library for advanced Text-to-Speech generation. It's built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed and quality. TTS comes with pretrained models, tools for measuring dataset quality and already used in 20+ languages for products and research projects.

📢 English Voice Samples and SoundCloud playlist

👨‍🍳 TTS training recipes

📄 Text-to-Speech paper collection

Please use our dedicated channels for questions and discussion. Help is much more valuable if it's shared publicly, so that more people can benefit from it.

"Mozilla*" and "Judy*" are our models. Details...

You can also help us implement more models. Some TTS related work can be found here.

TTS supports python >= 3.6, tts --text "Text for TTS" \ --model_name "///" \ --vocoder_name "///" \ --out_path folder/to/save/output/

Run your own TTS model (Using Griffin-Lim Vocoder)

Run your own TTS and Vocoder models

Note: You can use ./TTS/bin/synthesize.py if you prefer running tts from the TTS project folder.

Here you can find a CoLab notebook for a hands-on example, training LJSpeech. Or you can manually follow the guideline below.

To start with, split metadata.csv into train and validation subsets respectively metadata_train.csv and metadata_val.csv. Note that for text-to-speech, validation performance might be misleading since the loss value does not directly measure the voice quality to the human ear and it also does not measure the attention module performance. Therefore, running the model with new sentences and listening to the results is the best way to go.

To train a new model, you need to define your own config.json to define model details, trainin configuration and more (check the examples). Then call the corressponding train script.

For instance, in order to train a tacotron or tacotron2 model on LJSpeech dataset, follow these steps.

To fine-tune a model, use --restore_path.

To continue an old training run, use --continue_path.

For multi-GPU training, call distribute.py. It runs any provided train script in multi-GPU setting.

Each run creates a new output folder accomodating used config.json, model checkpoints and tensorboard logs.

In case of any error or intercepted execution, if there is no checkpoint yet under the output folder, the whole folder is going to be removed.

You can also enjoy Tensorboard, if you point Tensorboard argument--logdir to the experiment folder.

This repository is governed by Mozilla's code of conduct and etiquette guidelines. For more details, please read the Mozilla Community Participation Guidelines.

Feel free to ping us at any step you need help using our communication channels.

If you like to use TTS to try a new idea and like to share your experiments with the community, we urge you to use the following guideline for a better collaboration. (If you have an idea for better collaboration, let us know)