Audio Processing Python Packages

torchaudio

Data manipulation and transformation for audio signal processing, powered by PyTorch

soxr

Fast and high quality sample-rate conversion library for Python

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

asteroid-filterbanks

Asteroid's filterbanks :rocket:

nnaudio

Audio processing by using pytorch 1D convolution network

mlx-audio

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

pesq

PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)

stftpitchshift

STFT based real-time pitch and timbre shifting in C++ and Python

nvidia-dali-cuda120

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

spleeter

Deezer source separation library including pretrained models.

numpy-audio-limiter

Simple audio limiter. Made for use in audiomentations.

fast-mp3-augment

Fast Python library for MP3 audio data augmentation (encode + decode for intentional audio quality degradation). Made for use in audiomentations.

fast-bss-eval

A fast implementation of bss_eval metrics for blind source separation

auto-editor

Effort free video editing!

mediapipe-model-maker

Cross-platform, customizable ML solutions for live and streaming media.

basswood-av

Python bindings for ffmpeg libraries

mediapipe-nightly

Cross-platform, customizable ML solutions for live and streaming media.

mbrola

A Python front-end for the MBROLA speech synthesizer.

nara-wpe

Different implementations of "Weighted Prediction Error" for speech dereverberation

ffvoice

🎙️ 高性能 C++ 语音引擎 - 实时音频处理 + AI 语音识别 + 边录边转写 | High-performance C++ voice engine with real-time ASR and RNNoise

hear21passt

Inference code for PaSST, using the HEAR API.

vectorhub-nightly

Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors. (text2vec, image2vec, video2vec, graph2vec, bert, inception, etc)

dawdreamer

Digital Audio Workstation with Python; VST instruments/effects, parameter automation, FAUST, JAX, Warp Markers, and JUCE processors

klio-core

Smarter data pipelines for audio.