Explore live open-source projects and AI models.

Tacotron text to speech in C++(synthesize only)

This repository provides a multi-mode and multi-speaker expressive speech synthesis framework, including multi-attentive Tacotron, DurIAN, Non-attentive Tacotron, GST, VAE, GMVAE, and X-vectors for building prosody encoder.

No description available from source.

Tacotron2 with Global Style Tokens

Multi-speaker Tacotron in TensorFlow. 오픈소스 딥러닝 다중 화자 음성 합성 엔진.

style token with tacotron2

Reproducing Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis (https://arxiv.org/pdf/1803.09017.pdf)

MimicMania is a web application that allows you to generate speech and clone voices using text-to-speech technology. With MimicMania, you can create custom voices in a variety of languages and use them for a range of applications, from voiceovers to chatbots.

This is Pytorch Implementation of Google's Non-attentive Tacotron.

Gaussian Mixture VAE Tacotron