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 pre-trained models, tools for measuring dataset quality and is already used in 20+ languages for products and research projects. High-performance Deep Learning models for Text2Speech tasks. Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech). Speaker Encoder to compute speaker embeddings efficiently. Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN) Fast and efficient model training. Detailed training logs on the terminal and Tensorboard. Support for Multi-speaker TTS. Efficient, flexible, and lightweight but feature complete Trainer API. Released and ready-to-use models. Tools to curate Text2Speech datasets underdataset_analysis. Utilities to use and test your models.
Features
- Clone any voice from 3 seconds of audio and add to your collection
- Design your dream voice instead of choosing from a list
- Easily tune style of any voice, adjust pace and emotions
- Generative AI Emotions and Voice Control
- Voice Cloning
- Take full control of your AI voices. Adjust pitch, loudness and more, for each sentence, word or character
- Use takes to experiment and save different performances, deciding later which is the one
Project Samples
