Projects sharing features with Lyrebird

This project is a singing voice conversion tool based on VITS generative modeling. It transforms the identity of a singing voice to a target speaker while preserving the original melody, lyrics, and intonation. The system distinguishes itself through hybrid voice synthesis, allowing for the blending of multiple speaker identities via linear model interpolation. It utilizes cluster-based feature retrieval to increase target voice similarity and employs a diffusion probabilistic model as a post-processor to remove electronic artifacts and improve vocal clarity. The software covers a broad rang

This project is an AI singing voice conversion system and vocal processor used for training generative voice models and converting vocal recordings or live input into a target voice. It functions as a VITS model trainer and a real-time voice changer that transforms vocal timbre and pitch to change the identity of a singer. The system provides a graphical management dashboard for controlling training hyperparameters and voice conversion presets. It supports low-latency audio streaming for live microphone input and employs pitch estimation to ensure precise matching between source and target vo

Oboe is a native C++ library designed for building high-performance, low-latency audio applications on Android. It serves as a unified wrapper and native API for managing audio streams, sample rates, and hardware routing across different Android operating system versions. The library provides a consistent interface by automatically selecting the most efficient audio backend at runtime, switching between AAudio and OpenSL ES to ensure the lowest possible latency. It enables exclusive-mode hardware access to bypass the system mixer and utilizes a high-priority asynchronous pull model for audio

Voicevox is a text-to-speech synthesis software and audio production environment that converts written text into spoken audio using synthetic character voices. It functions as both a comprehensive editor for voice design and a standalone speech synthesis engine capable of generating audio via an API for integration into external applications. The project distinguishes itself by providing a singing voice synthesizer that uses a piano-roll interface for melodic vocal composition, including the ability to generate humming. It offers specialized prosody editing tools for the manual refinement of

This project is a comprehensive software suite for voice synthesis and model management, providing a framework for training custom acoustic models and performing voice conversion. It utilizes deep-learning-based acoustic modeling to map source audio characteristics to target voice identities, enabling the transformation of input audio into specific vocal profiles. The system distinguishes itself through a feature-retrieval-based inference mechanism, which employs vector index files to perform nearest-neighbor searches on acoustic features for high-fidelity timbre matching. Users can manage th

This software is a real-time voice changer that utilizes machine learning inference to transform live microphone input into target vocal characteristics. It functions as an artificial intelligence audio processing tool designed to modify vocal identity during active communication or live broadcasts. The application distinguishes itself by executing neural network models directly within the browser environment. It leverages web-based compute acceleration and dedicated audio threading to maintain low-latency performance, allowing users to switch between different voice profiles while processing

NoiseTorch is a cross-platform audio processor and real-time noise filter designed to suppress ambient sound from audio streams. It functions as a virtual microphone noise suppressor and routing tool, capturing system audio sources and directing filtered signals into virtual input or output devices. The application uses a recurrent neural network to distinguish between human speech and ambient noise. It provides a virtual denoising microphone that removes background noise from a selected input, alongside tools for filtering audio output streams. The system includes capabilities for audio dev

Virtual-Display-Driver is a kernel-level driver for Windows that emulates physical monitors and audio devices. It serves as a virtual monitor emulator, headless server display emulator, and virtual audio device driver to enable extended desktop space and sound routing on systems without physical hardware connections. The project enables the simulation of monitors with custom resolutions, refresh rates, and identification profiles, including support for High Dynamic Range output. It also provides software-defined audio interfaces to simulate virtual microphones and speakers. The software cove

VDO.Ninja is a low-latency peer-to-peer media routing service and video streaming platform designed to integrate remote audio and video feeds into professional production workflows. It functions as a WebRTC broadcast integration tool and studio controller, allowing for the direct transmission of high-definition media between publishers and viewers with minimal delay. The platform distinguishes itself through extensive protocol bridging, converting between WebRTC, WHIP, WHEP, SRT, and RTMP to ensure compatibility across diverse network environments and professional studio software. It includes

QuickRecorder is a screen recording software designed for capturing desktops, application windows, and system audio. It functions as a multi-device video recorder and tutorial capture tool, synchronizing video feeds from a computer and connected mobile devices into a single stream. The system distinguishes itself through an alpha-channel video exporter that produces recordings with transparent backgrounds. It also includes a presenter overlay system that renders a floating camera feed over screen captures and a specialized tutorial toolset that provides mouse movement highlighting and a magni

BackgroundMusic is a system-level macOS audio management utility that provides an application volume mixer for independent gain and level adjustments for every running application. It functions as a system audio router and pause controller to manage how sound is handled across the operating system. The project features a virtual audio driver that routes internal system sound to recording software and input devices. It also includes automatic music ducking, which monitors system audio activity to pause music playback when other applications produce sound and resume it once that audio ends. Th

Audio Router is a virtual audio routing tool used to redirect audio streams from specific software applications to chosen playback devices and hardware outputs. It functions as an application audio manager that allows for the assignment and saving of audio device preferences for individual running processes. The software includes capabilities for duplicating audio streams, enabling a single audio signal to be sent to multiple output devices simultaneously for synchronized playback. It also provides real-time audio monitoring through peak meters to visualize signal strength and audio levels ac

AudioNoise is a digital audio effects library and signal processor designed to manipulate audio waveforms through digital filtering and echo simulations. It functions as an analog circuit emulator, simulating the behavior of hardware guitar pedals and phasers. The project provides tools for experimental sound processing, including the generation of random digital noises and textures. It also includes an audio waveform visualizer that renders digital audio data as visual graphs to analyze the results of signal processing. The library implements capabilities for digital audio processing and an

THIS REPO IS NOT MAINTAINED ANYMORE. Please see https://codeberg.org/tenacityteam/tenacity for Tenacity, which is maintained.

x11docker is an OCI container GUI orchestrator and hardware bridge designed to execute graphical applications and full desktop environments inside containers. It functions as a Linux GUI sandbox, linking containerized processes to host X11 or Wayland display servers and audio systems. The project differentiates itself by providing deep system integration for hardware acceleration, including NVIDIA driver automation and GPU passthrough. It supports cross-architecture GUI emulation and provides remote access capabilities through VNC, SSH forwarding, and browser-based HTML5 rendering. The tool

Aubio is an audio analysis and digital signal processing library designed for music information retrieval. It provides a suite of tools for extracting musical features, estimating fundamental frequencies, and tracking rhythmic pulses in audio streams. The library specializes in the detection of pitch and beat, enabling the extraction of musical notes and the estimation of overall tempo. It also includes capabilities for automatic onset detection to identify the start of sonic events and the separation of audio signals into percussive transients and steady-state tonal components. The system c

This project is an AI voice training framework and singing voice conversion tool. It uses VITS and SoftVC technologies to transform the timbre of singing and spoken audio recordings, allowing a user to change the vocal characteristics of a recording to match a specific target speaker. The system provides a web-based voice converter interface for managing model checkpoints and performing timbre transformation and pitch shifting. It supports exporting trained models to the ONNX format for use in external interfaces and lightweight runtimes. The framework covers the full production pipeline, in

Surge is a polyphonic software synthesizer and VST plugin designed for complex sound generation. It functions as a hybrid synthesis engine, combining subtractive, wavetable, frequency modulation, and physical modeling techniques to produce audio. The project distinguishes itself through extensive microtuning capabilities, supporting non-standard musical scales and intonations via industry-standard tuning files. It also features an Open Sound Control compatible architecture for remote parameter management and hardware synchronization. The system covers a broad range of audio engineering capab

Nannou is a creative coding framework for Rust designed for building interactive visual and audio sketches. It provides a loop-based API with hardware-accelerated 2D and 3D rendering, serving as a toolkit for generative art production and multimedia installation design. The framework is distinguished by its comprehensive hardware communication interface, which bridges software with physical devices via MIDI, OSC, DMX, serial, and laser DAC protocols. It also includes specialized projection mapping tools for warping visual output to fit non-standard physical surfaces and a dedicated GPU shader

This project is an acoustic keystroke recognition system and audio side-channel analysis tool. It identifies typed text by analyzing audio recordings of keyboard sounds through waveform correlation and linguistic frequency analysis. The system distinguishes itself by combining digital signal processing with a substitution cipher decryptor. It uses simulated annealing and n-gram probability maps to recover plaintext from encoded strings and identifies specific keys by comparing captured waveforms against trained sound profiles. The toolkit covers a broad range of capabilities, including real-

This project is a multi-room music server and library aggregator that centralizes local audio files and various streaming services into a single unified database. It functions as a media controller for DLNA and UPnP devices, enabling the management of music, podcasts, and audiobooks across networked speakers. The system is distinguished by its ability to synchronize audio playback across multiple speakers and brands simultaneously. It features a digital signal processor for loudness normalization and frequency correction, alongside an acoustic fingerprinting engine used for metadata enrichmen

Overtone is a Lisp audio synthesis library that provides a programmable environment for designing synthesizers and generating real-time audio. It serves as a digital signal processing framework for live sound programming, integrating an audio sample manager for retrieving and caching sounds from remote repositories and a musical sequence generator for composing melodic and rhythmic structures. The project distinguishes itself through its specialized interfaces for hardware and networking, featuring a dedicated system for routing MIDI data and exchanging Open Sound Control messages between sof

wslg is an integration layer and display server system designed to run Linux graphical applications on Windows. It provides a bridge between Linux window management, audio routing, and system clipboards and the Windows host, utilizing a Wayland and X11 display server to support visual software. The system utilizes a virtual GPU architecture to provide hardware-accelerated rendering for graphics-intensive applications. It implements a Remote Desktop Protocol gateway to stream graphical frames and uses a specialized sound server interface to route audio and microphone data between the Linux gue

ALVR is a wireless virtual reality streaming tool and headset driver that transmits content from a PC to a headset over Wi-Fi to eliminate physical cables. It functions as a session orchestrator that manages a network-based pipeline for high-resolution frames and a virtual driver layer that enables a computer to communicate with and track wireless hardware. The system utilizes a UDP network protocol to synchronize compressed video frames and positional tracking data. It employs hardware-accelerated H.264 encoding to minimize lag and includes a virtual audio router to redirect microphone input

EZAudio is an audio library for Apple platforms that provides standardized interfaces for microphone capture, file playback, and hardware output. It functions as a low-latency audio processor and visualization framework designed to manipulate audio buffers and route signals with minimal delay. The project features a hardware-accelerated waveform renderer for drawing real-time audio amplitudes and rolling plots. It also includes a Fast Fourier Transform analyzer that converts time-domain audio samples into frequency-domain data for spectral analysis. The library covers a broad range of capabi