Speech Synthesis


Speech synthesis is the artificial production of human speech.

Overview

A 2019 Guide to Speech Synthesis with Deep Learning
A look at recent deep learning based speech synthesis research and techniques.
speech-synthesis wavenet tacotron voiceloop

Tutorials

Tacotron 2 (without wavenet)
PyTorch implementation with faster-than-realtime inference.
speech-synthesis tacotron tts speech

Libraries

General
Flowtron
Auto-regressive flow-based generative network for text to speech synthesis.
text-to-speech-synthesis tts flowtron tacotron
TensorflowTTS: Real-Time SOTA Speech Synthesis for Tensorflow 2.0
TensorflowTTS provides real-time state-of-the-art speech synthesis architectures such as Tacotron2, Melgan, FastSpeech.
text-to-speech-synthesis speech natural-language-processing speech-synthesis
Real-Time Voice Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time. Code for Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech.
speech-synthesis text-to-speech-synthesis sv2tts speech
Table of Contents
Share a project
Share something you or the community has made with ML.
Topic experts
Share