Tensorflowttsπ TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
Stars: β 2,382 (+2105.56%)
Zero-Shot-TTSUnofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Stars: β 33 (-69.44%)
ttslearnttslearn: Library for Pythonγ§ε¦γΆι³ε£°εζ (Text-to-speech with Python)
Stars: β 158 (+46.3%)
DurianImplementation of "Duration Informed Attention Network for Multimodal Synthesis" (https://arxiv.org/pdf/1909.01700.pdf) paper.
Stars: β 111 (+2.78%)
edittsOfficial implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech
Stars: β 74 (-31.48%)
Parallel-Tacotron2PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Stars: β 149 (+37.96%)
FastSpeech2PyTorch Implementation of FastSpeech 2 : Fast and High-Quality End-to-End Text to Speech
Stars: β 163 (+50.93%)
TensorVoxDesktop application for neural speech synthesis written in C++
Stars: β 140 (+29.63%)
Voice BuilderAn opensource text-to-speech (TTS) voice building tool
Stars: β 362 (+235.19%)
spokestack-androidExtensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
Stars: β 52 (-51.85%)
Fre-GAN-pytorchFre-GAN: Adversarial Frequency-consistent Audio Synthesis
Stars: β 73 (-32.41%)
StyleSpeechOfficial implementation of Meta-StyleSpeech and StyleSpeech
Stars: β 161 (+49.07%)
Cognitive Speech TtsMicrosoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
Stars: β 312 (+188.89%)
WsayWindows "say"
Stars: β 36 (-66.67%)
IMS-ToucanText-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart. Objectives of the development are simplicity, modularity, controllability and multilinguality.
Stars: β 295 (+173.15%)
WavegradImplementation of Google Brain's WaveGrad high-fidelity vocoder (paper: https://arxiv.org/pdf/2009.00713.pdf). First implementation on GitHub.
Stars: β 245 (+126.85%)
LightspeechLightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
Stars: β 31 (-71.3%)
open-speech-corporaπ A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
Stars: β 841 (+678.7%)
melganMelGAN implementation with Multi-Band and Full Band supports...
Stars: β 54 (-50%)
WavernnWaveRNN Vocoder + TTS
Stars: β 1,636 (+1414.81%)
Pytorch Dc TtsText to Speech with PyTorch (English and Mongolian)
Stars: β 122 (+12.96%)
Daft-ExprtPyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Stars: β 41 (-62.04%)
GttsPython library and CLI tool to interface with Google Translate's text-to-speech API
Stars: β 1,303 (+1106.48%)
MaryttsMARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
Stars: β 1,699 (+1473.15%)
DiffwaveDiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
Stars: β 139 (+28.7%)
LVCNetLVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation
Stars: β 67 (-37.96%)
Aeneasaeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
Stars: β 1,942 (+1698.15%)
LingvoLingvo
Stars: β 2,361 (+2086.11%)
MelNet-SpeechGenerationImplementation of MelNet in PyTorch to generate high-fidelity audio samples
Stars: β 19 (-82.41%)
Spokestack PythonSpokestack is a library that allows a user to easily incorporate a voice interface into any Python application.
Stars: β 103 (-4.63%)
Athenaan open-source implementation of sequence-to-sequence based speech processing engine
Stars: β 542 (+401.85%)
TtsText-to-Speech for Arduino
Stars: β 118 (+9.26%)
CrystalCrystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.
Stars: β 108 (+0%)
talkieText-to-speech browser extension button. Select text on any web page, and have the computer read it out loud for you by simply clicking the Talkie button.
Stars: β 43 (-60.19%)
WaveGrad2PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
Stars: β 55 (-49.07%)
esp32-fliteSpeech synthesis running on ESP32 based on Flite engine.
Stars: β 28 (-74.07%)
Comprehensive-Tacotron2PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
Stars: β 22 (-79.63%)
WavegradA fast, high-quality neural vocoder.
Stars: β 138 (+27.78%)
Multilingual text to speechAn implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
Stars: β 324 (+200%)
Ttsπ€ π¬ Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Stars: β 5,427 (+4925%)
TtsπΈπ¬ - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Stars: β 305 (+182.41%)
TFGANTFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
Stars: β 65 (-39.81%)
Hifi GanHiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Stars: β 325 (+200.93%)
Glow TtsA Generative Flow for Text-to-Speech via Monotonic Alignment Search
Stars: β 284 (+162.96%)
Transformer TtsA Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
Stars: β 418 (+287.04%)
VAENAR-TTSPyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
Stars: β 66 (-38.89%)
CboardAAC communication system with text-to-speech for the browser
Stars: β 437 (+304.63%)
vitsVITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Stars: β 1,604 (+1385.19%)
Cross-Speaker-Emotion-TransferPyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Stars: β 107 (-0.93%)
Expressive-FastSpeech2PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
Stars: β 139 (+28.7%)
FastSpeech2Multi-Speaker Pytorch FastSpeech2: Fast and High-Quality End-to-End Text to Speech β
Stars: β 64 (-40.74%)
ParakeetPAddle PARAllel text-to-speech toolKIT (supporting WaveFlow, WaveNet, Transformer TTS and Tacotron2)
Stars: β 279 (+158.33%)
ParallelwaveganUnofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN) with Pytorch
Stars: β 682 (+531.48%)
Jsut LabHTS-style full-context labels for JSUT v1.1
Stars: β 28 (-74.07%)
Cs224n Gpu That TalksAttention, I'm Trying to Speak: End-to-end speech synthesis (CS224n '18)
Stars: β 52 (-51.85%)
EMPHASIS-pytorchEMPHASIS: An Emotional Phoneme-based Acoustic Model for Speech Synthesis System
Stars: β 15 (-86.11%)
Openseq2seqToolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
Stars: β 1,378 (+1175.93%)
JoytanCreative Audio/Textbook Maker π΅ π See our YouTube channel
Stars: β 91 (-15.74%)