Open-source alternatives to Jukebox

This project is a TensorFlow implementation of a neural network for raw audio waveform generation. It functions as a conditioned speech synthesis model that produces synthetic audio samples using a dilated convolutional neural network architecture. The system supports custom voice modeling by incorporating global conditioning and categorical identifiers during training and generation. This allows the model to mimic specific speakers or distinct audio characteristics for neural text-to-speech applications. The framework covers deep learning audio synthesis, including audio dataset processing,

Zonos is a controllable audio synthesis engine and large language model for text-to-speech. It serves as a multilingual speech generator capable of producing audio in English, Japanese, Chinese, French, and German. The system provides zero-shot voice cloning, allowing the replication of specific human voices using short audio samples. It supports the capture of nuanced behaviors, such as whispering, and provides parametric control over speaking rate, pitch, frequency, and emotional tone. The project covers a broad range of expressive speech synthesis and custom audio generation capabilities,

This Python SDK provides a comprehensive toolkit for synthetic audio generation, voice cloning, and the development of conversational AI agents. It enables the creation of lifelike spoken audio from text, the replication of human voices through custom cloning, and the deployment of real-time voice agents capable of interacting with external large language models. The library distinguishes itself through deep integration of conversational AI capabilities, including the design of agent personas and the execution of real-time actions via APIs. It supports professional-grade audio production thro

CSM is a conversational speech generation model and text-to-speech engine that converts text and audio inputs into synthetic speech. It utilizes a large language model architecture to predict and decode audio tokens for voice synthesis. The system functions as a zero-shot voice cloner, replicating specific speaker identities using short audio samples without requiring additional training. This enables precise control over speaker identity and the creation of synthetic speech that mimics a specific person. The model covers conversational speech synthesis and text-to-speech generation, transfo

Magenta is an AI creative suite and TensorFlow generative art framework used to train and deploy models for the production of artistic media. It functions as a generative music library and a deep learning art generator, providing tools to automate the creation of original musical compositions and visual artwork. The project covers AI music composition and generative visual art through neural art generation and machine learning creativity. It enables the training of generative models to produce original songs, images, and drawings based on learned patterns.

This project is an educational course and collection of training materials focused on generative diffusion models. It provides a curriculum and practical guides for training, fine-tuning, and deploying models capable of synthesizing images, audio, and video. The material covers specific implementation strategies including noise-based synthesis, iterative refinement, and latent space compression. It provides instruction on guiding generative outputs through conditional synthesis and prompt adherence optimization, as well as techniques for image inpainting and text-based editing. The project i

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Stable-audio-tools is a toolkit for training and deploying latent diffusion models for high-fidelity audio synthesis. It provides a framework for generating audio by iteratively refining noise within a compressed latent space, using specialized encoders to preserve temporal and spectral features of the audio signal. The project features a system for adapting pre-trained audio checkpoints to new datasets through modular initialization and configuration files. It includes utilities for weight extraction and inference model export, which remove training metadata and optimizer states to create li

VALL-E-X is a neural speech synthesis framework and zero-shot text-to-speech engine. It functions as a multilingual synthesizer capable of generating natural human speech with control over emotion, pitch, and prosody. The project specializes in zero-shot voice cloning and cross-lingual voice replication, allowing the system to produce personalized speech in multiple target languages using short audio samples without additional training. It further enables cross-language accent manipulation and the ability to match the emotional tone and acoustic environment of a provided prompt. The implemen

nlp-recipes is a collection of implementation guides and reference templates for applying natural language processing techniques to real-world tasks. It provides standardized workflows and code examples for developing NLP pipelines, from dataset preparation and model training to performance evaluation. The project focuses on the practical application of transformer-based models, offering patterns for fine-tuning pretrained architectures for tasks such as text classification, named entity recognition, and question answering. It also includes a toolkit for model interpretability, allowing users

document.ai is a local document question-answering system and vector database search engine. It functions as a retrieval-augmented generation knowledge base that combines a vector database with language models to generate answers grounded in private local datasets. The project features a domain-specific embedding pipeline and a fine-tuned language model framework. These tools allow for the use of specialized embedding models and mathematical theme extraction to improve retrieval accuracy for professional terminology and technical subject areas. The system covers vector-based semantic retriev

This is a machine learning framework for treating diverse natural language processing tasks as a unified text-to-text problem. It provides a toolkit for pre-training and fine-tuning large-scale transformer models, utilizing a system where both inputs and outputs are formatted as raw text sequences. The framework is distinguished by its distributed training system, which uses mesh-based strategies to scale model weights and training batches across multiple TPU cores. It supports multi-task learning by combining diverse datasets into a single training stream using configurable mixture rates, al

This repository provides a collection of reference implementations and code examples for training and deploying machine learning models using the MLX framework. It serves as a practical guide for executing distributed training, fine-tuning large language models, converting model weights, and implementing multimodal generative workflows. The project distinguishes itself through specialized examples for local hardware execution, featuring weight quantization to reduce memory usage and low-rank adaptation for parameter-efficient fine-tuning. It also includes scripts for transforming external mod

DeepKE is a knowledge extraction toolkit and framework designed to transform unstructured text into structured knowledge graphs. It provides a pipeline for identifying and classifying named entities, semantic relations, and events, converting raw datasets into structured triples. The project utilizes large language models as tool callers through a standardized context protocol to drive automated data extraction processes. It supports schema-driven extraction across multiple domains and bilingual text, employing joint entity and relation extraction to identify components in a single structured

Magenta is a comprehensive toolkit for training, synthesizing, and performing music through neural models and hardware-integrated engines. It functions as a machine learning framework that enables the generation, manipulation, and real-time performance of audio, providing the structural foundations for musical intelligence through hierarchical sequence modeling and symbolic processing. The project distinguishes itself by enabling real-time, low-latency neural audio synthesis that can be integrated directly into professional digital audio workstations. It supports interactive musical jamming a

Amphion is an audio generation toolkit designed for the research and development of models that synthesize speech, music, and environmental sound effects. It provides a standardized framework for reproducible audio synthesis, incorporating a text-to-speech engine and a voice conversion framework. The project specializes in transforming audio identities, allowing for the modification of speaker accents and voice identities while preserving original rhythm and style. It also includes capabilities for singing voice synthesis and the generation of environmental soundscapes from text descriptions

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

An audio server, programming language, and IDE for sound synthesis and algorithmic composition.

JUCE is a comprehensive C++ audio framework and digital signal processing library used to build cross-platform audio applications, audio plug-ins, and high-performance user interfaces. It serves as a development kit for creating audio processors compatible with industry-standard plugin formats for digital audio workstations, as well as a tool for MIDI and Open Sound Control communication between musical hardware and software. The framework is distinguished by its ability to maintain a single codebase for native desktop and mobile applications across multiple operating systems. It provides a f

YouDub-webui is a multilingual video translator and AI dubbing pipeline manager featuring a web interface for automating video translation, audio dubbing, and subtitle burning. It utilizes a GPU-accelerated media processor to speed up audio transcription and video rendering tasks. The system implements a stage-based pipeline that converts original speech into new languages while preserving background audio through audio track mixing. It supports multiple localization workflows, including automated translation and subtitle-driven dubbing using SRT files to bypass automatic transcription phases

LMMS is a digital audio workstation and MIDI sequencer designed for composing, arranging, and mixing music. It functions as a comprehensive production environment that integrates a MIDI sequencer, a sample-based synthesizer, and an audio mixing console. The project distinguishes itself through a versatile synthesis engine that includes additive synthesis, wavetable generation, and emulations of vintage hardware such as NES audio and FM chips. It also serves as a VST plugin host, allowing for the integration of third-party virtual instruments and audio effects via a standardized interface. Be

VideoLingo is an automated video localization suite designed to transcribe, translate, and dub video content. It functions as a translation pipeline that utilizes large language models to convert spoken audio into precise text segments and translate them into multiple languages. The system differentiates itself through a multi-step translation refinement process and a specialized natural language processing utility that segments text into single-line captions meeting broadcast standards. It also integrates synthetic voiceover generation to replace or augment original audio tracks. The projec

Muzic is a deep learning platform and framework for AI-driven music analysis, composition, and synthesis. It functions as a music generation framework and analysis tool, utilizing large language models and autonomous agents to orchestrate the creation and interpretation of symbolic and audio music. The project is distinguished by its cross-modal capabilities, mapping natural language and symbolic music into a shared joint embedding space for zero-shot classification and information retrieval. It employs a variety of specialized architectures, including diffusion frameworks for audio synthesis

Scribbletune is a JavaScript music composition library, MIDI file generator, text-based patch diagrammer, and Web Audio API sequencer. It enables the definition of rhythms, chords, and melodies using string-based notation for real-time playback in web browsers. The system transforms simple text notation into SVG visual representations of modular synthesizer signal paths. It also converts programmatically composed musical clips and patterns into standard MIDI files for use in external digital audio workstations. Composition capabilities include a character-based rhythmic notation system for p

AudioKit is an audio framework for iOS, macOS, and tvOS that provides tools for digital audio synthesis, signal processing, and audio analysis. It functions as a synthesis engine for generating audio waveforms and textures, a processing library for modifying tonal characteristics, and a toolkit for extracting frequency and amplitude data from sonic signals. The framework utilizes a modular node architecture and graph-based signal routing to connect audio generators, processors, and outputs. It wraps low-level audio primitives in high-level classes to facilitate sound generation and modificati

Pyxel is a Python-based retro game engine designed for creating pixel-art applications with vintage aesthetics. It functions as a pixel art framework that emulates classic hardware limitations through fixed-resolution displays, constrained color palettes, and a 2D tilemap engine for rendering scaled sprites and grid-based game worlds. The engine features a dedicated MML audio synthesizer that uses Macro Language notation to compose and play back retro-style sound sequences. It also includes capabilities for seed-based background music generation and the playback of raw PCM audio data for cust

This project is a set of digital signal processing routines and firmware designed for building modular synthesis hardware and control voltage modules. It functions as a comprehensive system for Eurorack synthesis, incorporating a physical modeling synthesis engine, a granular synthesis module, and a dedicated control voltage processor. The system distinguishes itself through a specialized synthesis engine that simulates the acoustic properties of strings, reeds, and percussion using modal resonators. It also features a MIDI to CV converter for monophonic and polyphonic operation and a step se