Audio Noise Reduction Voice AI Tools

There are 25 audio noise reduction tools tracked. 1 score above 70 (verified tier). The highest-rated is descriptinc/descript-audio-codec at 72/100 with 1,732 stars and 453,067 monthly downloads.

Get all 25 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=voice-ai&subcategory=audio-noise-reduction&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	descriptinc/descript-audio-codec State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz,...	72	Verified	1,732	Python
2	crlandsc/torch-log-wmse logWMSE, an audio quality metric & loss function with support for digital...	47	Emerging	45	Python
3	drethage/speech-denoising-wavenet A neural network for end-to-end speech denoising	44	Emerging	708	Python
4	KyungsuKim42/tokensynth The official implementation of TokenSynth (ICASSP 2025)	44	Emerging	81	Python
5	iver56/torch-audiomentations Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful...	43	Emerging	1,136	Python
6	YuanGongND/ast Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".	43	Emerging	1,432	Jupyter Notebook
7	madhavmk/Noise2Noise-audio_denoising_without_clean_training_data Source code for the paper titled "Speech Denoising without Clean Training...	40	Emerging	208	Jupyter Notebook
8	lmnt-com/wavegrad A fast, high-quality neural vocoder.	40	Emerging	296	Python
9	slp-rl/aero This repo contains the official PyTorch implementation of "Audio Super...	39	Emerging	237	Python
10	kkoutini/PaSST Efficient Training of Audio Transformers with Patchout	39	Emerging	370	Python
11	lucadellalib/focalcodec A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation	38	Emerging	152	Jupyter Notebook
12	vb000/Waveformer A deep neural network architecture for low-latency audio processing	35	Emerging	323	Python
13	maum-ai/wavegrad2 Unofficial Pytorch Implementation of WaveGrad2	33	Emerging	112	Jupyter Notebook
14	RoySheffer/im2wav Official implementation of the pipeline presented in I hear your true...	33	Emerging	124	Python
15	maum-ai/nuwave2 NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling...	33	Emerging	307	Python
16	hmartelb/speech-denoising Speech Denoising project for the Deep Learning course at Tsinghua...	32	Emerging	18	Jupyter Notebook
17	JusperLee/Conv-TasNet Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech...	32	Emerging	535	Python
18	erogol/FFTNet FFTNet vocoder implementation	30	Emerging	81	Jupyter Notebook
19	richardassar/SampleRNN_torch Torch implementation of SampleRNN: An Unconditional End-to-End Neural Audio...	29	Experimental	156	Lua
20	samsad35/source-filter-vae [SpeechCom Journal] Learning and controlling the source-filter...	28	Experimental	45	Python
21	audo-ai/magic-mic Open Source Noise Cancellation App for Virtual Meetings	27	Experimental	384	C++
22	YChenL/DS-TDNN Official implement of "Dual-stream Time-Delay Neural Network with Dynamic...	25	Experimental	41	Python
23	echocatzh/GTCNN Personalized AEC	22	Experimental	19	HTML
24	kyegomez/SoundStream Implementation of SoundtStream from the paper: "SoundStream: An End-to-End...	20	Experimental	13	Python
25	DanteUrdaneta/CENSORSHIP.PY Censorship Audio is a Python library that allows you to censor specific...	12	Experimental	13	Python

Comparisons in this category

descript-audio-codec and focalcodec (72 vs 38)