Open Source Audio Processing Projects
Audio processing uses software to capture, transform, analyze, and generate sound. It supports tasks such as filtering noise, adjusting effects, converting formats, extracting features, and preparing speech or music for playback, transcription, and machine learning. These tools help make audio clearer, more accessible, and suitable for different applications and devices.
Open source options include audio libraries, signal analysis frameworks, effect processors, speech tools, and applications for editing or streaming sound. When choosing one, consider its license, maintenance activity, documentation, supported formats, performance requirements, and compatibility with your existing workflow. These tools are useful to developers, researchers, musicians, media teams, and anyone building audio features or processing recordings.
8 repositories · updated June 22, 2026
EasyWhisperUI: A Cross-Platform Desktop App for Whisper Model Transcription
EasyWhisperUI is a fast, local desktop application designed for transcribing audio and video using the Whisper model. It offers GPU acceleration across Windows, macOS, and Linux, providing a user-friendly interface for various transcription tasks. The application supports features like live transcription, batch processing, and translation, making it a versatile tool for media processing.
TimeSide: A Scalable Python Framework for Audio Processing and Analysis
TimeSide is a powerful Python framework designed for scalable audio processing, analysis, imaging, transcoding, streaming, and labeling. It offers a core Python module, a web server with a RESTful API, and a JavaScript SDK. This framework is ideal for complex processing on large audio or video datasets, supporting diverse applications from computational musicology to streaming services.
Kapre: Keras Audio Preprocessors for Real-time GPU Processing
Kapre is a powerful Python library that provides Keras layers for real-time audio preprocessing directly on GPUs. It enables efficient computation of STFT, Melspectrograms, and other audio features within your deep learning models. This integration simplifies model deployment, allows for DSP parameter optimization, and ensures consistency compared to traditional pre-computation or custom implementations.
index-tts-lora: High-Quality Speech Synthesis with LoRA Fine-tuning
index-tts-lora offers a robust solution for high-quality speech synthesis, leveraging LoRA fine-tuning on the index-tts framework. It significantly enhances prosody and naturalness for both single and multi-speaker voices. This project provides practical methods for training and inference, making advanced voice synthesis more accessible.
Diffusion Studio Core: Browser-Based Video Compositing Engine
Diffusion Studio Core is a powerful, browser-based video compositing engine built with TypeScript. It leverages WebCodecs and Canvas2D for hardware-accelerated media processing directly within the browser. Designed for developers building non-linear editors, it supports both interactive playback for editing and high-fidelity rendering for final output across video, audio, and image workloads.
Fast Music Remover: Lightweight Music and Noise Removal for Media
Fast Music Remover is a C++ based, lightweight tool designed for efficient music and noise removal from YouTube and other internet media. It leverages DeepFilterNet for advanced audio enhancement, empowering users to take control of their media consumption. The project offers a modular, cross-platform solution with both a web UI and containerized deployment options.
parakeet-mlx: Nvidia's Parakeet ASR Models on Apple Silicon with MLX
parakeet-mlx is an open-source project that implements Nvidia's advanced Automatic Speech Recognition (ASR) Parakeet models for Apple Silicon, leveraging the MLX framework for optimized performance. This Python library offers both a command-line interface and a flexible Python API, enabling efficient transcription of audio files, including real-time streaming capabilities. It provides a powerful solution for developers and researchers working with speech processing on Apple hardware.
Pedalboard: Spotify's Python Library for Audio Effects and Machine Learning
Pedalboard is a robust Python library developed by Spotify's Audio Intelligence Lab, designed for comprehensive audio processing tasks. It facilitates reading, writing, rendering, and applying a wide array of audio effects, including support for VST3® and Audio Unit plugins. Internally, Spotify leverages Pedalboard for data augmentation to enhance machine learning models and power innovative features like AI DJ, making advanced audio manipulation accessible within Python and TensorFlow environments.