Neural Vocoder Implementations Voice AI Tools

Tools and models for converting mel-spectrograms or acoustic features into high-fidelity waveforms using neural networks (GANs, diffusion, autoregressive models). Does NOT include end-to-end TTS systems, speech recognition, or general audio processing.

There are 77 neural vocoder implementations tools tracked. 3 score above 50 (established tier). The highest-rated is kan-bayashi/ParallelWaveGAN at 51/100 with 1,637 stars.

Get all 77 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=voice-ai&subcategory=neural-vocoder-implementations&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	kan-bayashi/ParallelWaveGAN Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN &...	51	Established	1,637	Jupyter Notebook
2	fatchord/WaveRNN WaveRNN Vocoder + TTS	51	Established	2,179	Python
3	shangeth/wavencoder WavEncoder is a Python library for encoding audio signals, transforms for...	50	Established	92	Python
4	rishikksh20/iSTFTNet-pytorch iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating...	49	Emerging	274	Python
5	seungwonpark/melgan MelGAN vocoder (compatible with NVIDIA/tacotron2)	49	Emerging	650	Python
6	lucasnewman/best-rq-pytorch Implementation of BEST-RQ - a model for self-supervised learning of speech...	48	Emerging	133	Python
7	rishikksh20/VocGAN VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested...	47	Emerging	321	Python
8	Deepest-Project/MelNet Implementation of "MelNet: A Generative Model for Audio in the Frequency Domain"	47	Emerging	210	Python
9	tiberiu44/TTS-Cube End-2-end speech synthesis with recurrent neural networks	47	Emerging	223	Python
10	npuichigo/waveglow A PyTorch implementation of the WaveGlow: A Flow-based Generative Network...	46	Emerging	205	Python
11	HAKORADev/VODER Voice Operation and Design Engine with Reproduction capabilities	45	Emerging	116	Python
12	rishikksh20/Fre-GAN-pytorch Fre-GAN: Adversarial Frequency-consistent Audio Synthesis	45	Emerging	111	Python
13	jishengpeng/WavTokenizer [ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second...	44	Emerging	1,279	Python
14	yerfor/SyntaSpeech SyntaSpeech: Syntax-aware Generative Adversarial Text-to-Speech; IJCAI 2022;...	44	Emerging	203	Python
15	rishikksh20/TFGAN TFGAN: Time and Frequency Domain Based Generative Adversarial Network for...	44	Emerging	88	Python
16	keonlee9420/PortaSpeech PyTorch Implementation of PortaSpeech: Portable and High-Quality Generative...	43	Emerging	341	Python
17	rishikksh20/melgan MelGAN implementation with Multi-Band and Full Band supports...	43	Emerging	62	Jupyter Notebook
18	keonlee9420/WaveGrad2 PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement...	43	Emerging	69	Python
19	zceng/LVCNet LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation	43	Emerging	80	Python
20	AmphionTeam/FlexiCodec [ICLR2026] FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates	43	Emerging	42	Python
21	BogiHsu/WG-WaveNet Real-Time High-Fidelity Speech Synthesis without GPU	42	Emerging	73	Python
22	34j/neural-source-filter Python package for NSF and NSF-HiFi-GAN (unofficial)	42	Emerging	7	Python
23	hcy71o/AutoVocoder Autovocoder: Fast Waveform Generation from a Learned Speech Representation...	42	Emerging	71	Python
24	tuan3w/cnn_vocoder A fast cnn-based vocoder	41	Emerging	78	Python
25	modelscope/FunCodec FunCodec is a research-oriented toolkit for audio quantization and...	41	Emerging	442	Python
26	rishikksh20/Avocodo-pytorch Avocodo: Generative Adversarial Network for Artifact-free Vocoder	40	Emerging	122	Python
27	warisqr007/vocos Causal version of Vocos (neural vocoders for high-quality audio synthesis)...	39	Emerging	2	Jupyter Notebook
28	cvqluu/TDNN Time delay neural network (TDNN) implementation in Pytorch using unfold method	39	Emerging	204	Python
29	rishikksh20/UnivNet-pytorch UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators...	38	Emerging	76	Python
30	Rongjiehuang/Multiband-WaveRNN An unofficial implement of autoregressive vocoder Multiband-WaveRNN. Audio...	37	Emerging	28	Python
31	zsl24/Tacotron2-Mandarin-HiFiGAN Implementation of TTS with combination of Tacotron2 and HiFi-GAN	37	Emerging	11	Python
32	andi611/Conditional-SpecGAN-Tensorflow Text-to-Speech Synthesis by Generating Spectrograms using Generative...	37	Emerging	10	Python
33	hhguo/SoCodec Ultra-low-bitrate Speech Codec for Speech Language Modeling Applications	37	Emerging	90	Python
34	rishikksh20/iSTFT-Avocodo-pytorch Ultrafast GAN based Vocoder for Text to Speech	37	Emerging	50	Python
35	Fraunhofer-AISEC/towards-resistant-audio-adversarial-examples Generation tool for offset-resistant audio adversarial examples against Deepspeech	36	Emerging	10	Python
36	HarunoriKawano/BEST-RQ Implementation of the paper "Self-supervised Learning with Random-projection...	35	Emerging	91	Python
37	maetshju/flux-blstm-implementation An implementation of the Graves & Schmidhuber (2005) bidirectional LSTM in Flux.	35	Emerging	11	Julia
38	WindQAQ/tensorflow-wavenet Implementation of WaveNet network based on Tensorflow.	35	Emerging	9	Python
39	candlewill/AiVoice Deep CNN networks for Speech Synthesis	34	Emerging	49	Python
40	philsyn/DiffWave-Vocoder Pytorch Reimplementation of DiffWave Vocoder: a high quality, fast, and...	34	Emerging	90	Python
41	vliu15/adversarial-tts End-to-end Text-to-Speech with Generative Adversarial Networks	34	Emerging	20	Python
42	anooptoffy/DLJeju2018CodeRepoASR Details on my work on using GANs for speech synthesis for improving Speech...	33	Emerging	8	—
43	lucadellalib/audiocodecs A collections of audio codecs with a standardized API	33	Emerging	36	Python
44	ryhorv/tf-flowavenet Tensorflow implementation of "FloWaveNet: A Generative Flow for Raw Audio"	33	Emerging	25	Jupyter Notebook
45	nilakshdas/ADAGIO Adversarial Defense for Audio in a Gadget with Interactive Operations	32	Emerging	5	Python
46	zzw922cn/LPC_for_TTS Linear Prediction Coefficients estimation from mel-spectrogram implemented...	32	Emerging	71	Python
47	Barbany/Multi-speaker-Neural-Vocoder Bachelor's thesis carried at Universitat Politecnica de Catalunya in partial...	31	Emerging	16	Python
48	azraelkuan/FFTNet FFTNet: a Real-Time Speaker-Dependent Neural Vocoder	31	Emerging	64	Python
49	diggerdu/pytorch_audio audio processing module for pytorch:stft, istft	31	Emerging	36	Python
50	warisqr007/vq-bnf Vector Quantizing speech representations	31	Emerging	4	Python
51	rafaelvalle/asrgen Attacking Speaker Recognition with Deep Generative Models	30	Emerging	34	Jupyter Notebook
52	khaykingleb/hifi-gan Neural vocoder for high-fidelity speech synthesis (implementation of the...	29	Experimental	1	Python
53	DillionLowry/NeuralCodecs Neural Audio Codecs implemented in C# - DAC, SNAC, Encodec, Dia	29	Experimental	45	C#
54	jik876/hifi-gan-demo Audio samples from "HiFi-GAN: Generative Adversarial Networks for Efficient...	28	Experimental	10	HTML
55	hi-paris/wavlm-vocoder-french WavLM-to-Audio neural vocoder for French speech reconstruction — layer...	28	Experimental	18	Python
56	dimitriStoidis/GenGAN Repository for the paper: Generating gender-ambiguous voices for...	28	Experimental	8	Python
57	p1an-lin-jung/WavThruVec_pytorch An implementation of Charactr, Inc's "WavThruVec: Latent speech...	27	Experimental	29	Python
58	Xinghui-Wu/KENKU KENKU: Towards Efficient and Stealthy Black-box Adversarial Attacks against...	27	Experimental	20	Python
59	aminul-huq/Adversarial-Examples-For-Audio-Data Repo for papers to read on adversarial attack and defense techniques in the...	25	Experimental	41	—
60	PeechApp/tts-peech DelightfulTTS with Hifi-GAN and Univnet vocoders	25	Experimental	8	Jupyter Notebook
61	egorsmkv/radtts-hifigan RADTTS + HiFiGAN vocoder	25	Experimental	7	Python
62	ZhanpengWang96/pytorch-speech2vec Pytorch implementation of the paper Speech2Vec: A Sequence-to-Sequence...	24	Experimental	5	Jupyter Notebook
63	NTT123/hifigan-tpu Train HiFi-GAN on TPU	21	Experimental	10	Python
64	will-rice/diffwave TensorFlow 2.0 Implementation of DiffWave: A Versatile Diffusion Model for...	20	Experimental	8	Python
65	diver-j/melgan-multi MelGAN Multi GPU Implementation.	20	Experimental	8	Python
66	mzyICT/MSDGAN 基于对刚生成网络的语音降噪	19	Experimental	4	MATLAB
67	rishikksh20/voxtral-codec-pytoch Voxtral Codec : Combining Semantic VQ and Acoustic FSQ for Ultra-Low Bitrate...	19	Experimental	9	Python
68	che-roman/mb-melgan Unofficial implementation of Multi-band MelGAN	17	Experimental	1	Python
69	StellarTerror/NeuralVocoders Implementations of HiFi-GAN, iSTFTNet and MISRNet	17	Experimental	1	Python
70	neyudin/wavenetglow Main repository for the "Modern Methods of Speech Recognition and Synthesis"...	17	Experimental	1	Python
71	Orca0917/Spectrogram-VQ Unofficial implementation of Spectrogram VQ from DCTTS paper - Vector...	15	Experimental	—	Jupyter Notebook
72	mmatlin/formant-encoder An encoder which compresses audio data based on prominent acoustic features...	12	Experimental	5	Python
73	ksoh97/MelGAN-Waveform-synthesis Pytorch re-implementation of MelGAN: Generative Adversarial Networks for...	11	Experimental	3	Python
74	testzer0/MetricGAN-Reloaded An implementation of the paper MetricGAN (ICML 2019) in pytorch with some changes.	11	Experimental	3	Jupyter Notebook
75	HondamunigePrasannaSilva/CLAR Pytorch implementation of CLAR: Contrastive Learning of Auditory Representations	11	Experimental	3	Python
76	yandex-research/proxy-dirichlet-distillation Implementation of "Scaling Ensemble Distribution Distillation to Many...	11	Experimental	4	Python
77	nickovchinnikov/tts-framework DelightfulTTS + UnivNet or HifiGAN	11	Experimental	4	Jupyter Notebook

Comparisons in this category

WaveRNN and waveglow (51 vs 46) WaveRNN and WaveGrad2 (51 vs 43)