generative-audio
Projects tagged with generative-audio on GitHub.
43 projects
procedural-sounds
TypeScriptProcedural interface sounds, with taste. Generated live in the browser from recipes, steered by a hand-curated library and calibrated by ear. No audio files. Beta, open to collaborators.
LocalAI
GoLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
MAGI-2-preview
PythonMAGI-2-preview: Scaling Video Generation Models Efficiently
ComfyUI-Spectrum-MiniMax-H3
PythonSpectrum-based acceleration for ComfyUI’s native MiniMax H3 audio-video model. Forecasts post-transformer features with Chebyshev ridge regression to skip selected transformer evaluations, with adaptive scheduling, sampler-aware safeguards, CPU/VRAM history storage, and native fallbacks.
Audio8_TTS
PythonSOTA-Class TTS at Compact Scale
threejs-game-skills
PythonAgent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.
ComfyUI
PythonThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
generative-ai-for-beginners
Jupyter Notebook21 Lessons, Get Started Building with Generative AI
Audar-ASR-V1
PythonArabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.
appless
TypeScriptWhat if your phone had no apps
Krbn
TypeScriptA web engine for pencil-style rendering of 3D scenes to SVG — exact silhouettes, hidden-line ghosting, hatching. Great for abstract and technical scenes.
langflow
PythonLangflow is a powerful tool for building and deploying AI-powered agents and workflows.
geolook
PythonOpen-source end-to-end GEO implementation: status analysis, diagnosis, strategy, tickets, execution, verification
img2threejs
PythonRebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
lottie
TypeScriptGenerate production-ready Lottie animations with Claude Code or Codex
lore
RustLore is a next-generation, open source version control system
gc-minimal-zine-poster
Codex skill for generating quiet minimal zine-style editorial poster prompts and images.
sideshow
TypeScriptThe missing visual surface companion for agents - generate UI mockups, data visualizations, code explainers, and more
ragflow
GoRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Boogu-Image
PythonBoogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.
MoneyPrinterTurbo
Python利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
Claude-of-Duty
JavaScriptA Call of Duty-quality FPS in Three.js, built from a single prompt.
eterna-image2image-skill
Experimental bilingual Codex skill for ETERNA-inspired image2image cinematic color and composition.
PixelRAG
PythonThe end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
jungle-trail
JavaScriptA fully procedural first-person jungle in Three.js. Zero external art assets - every texture, mesh and sound generated in code.
ip-as-logo-skill
A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.
wardrobe
JavaScriptYour clothes, extracted and organized with gpt-image.
football-stadium
HTMLA 3D football stadium to visualize where you sit in the seat before you buy it
sakura-crossing
JavaScriptAn explorable Japanese suburban railway-crossing neighbourhood on a small planet, rendered 3D-to-2D as a cel-shaded anime background. Three.js, no image assets.
sylva
HTMLAn interactive Three.js landscape study with a procedural, pointer-responsive moss world.
sample-specship
ShellSpec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.
klaatcode
TypeScriptOpen-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.
marketing-studio
JavaScriptAgent-driven marketing studio for Claude Code: one /marketing command renders your product's full launch asset suite (logo reveal, demo, launch video, social clips, OG assets)
CodeJury
PythonTerminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.
react-native-system-thumbnails
KotlinNative iOS and Android system thumbnails for React Native, with caching, cancellation, and icon fallbacks.
gorest-2d-animation-spritesheet-generator
TypeScriptCodex-assisted local 2D animation spritesheet generator and scene compositing workspace.
ponytail
JavaScriptMakes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
beautiful-html-templates
HTMLA library of HTML slide templates designed so any coding agent can pick the right one and produce a beautiful deck on the user's behalf, automatically.
agent-apprenticeship
PythonThe living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
MLX-LoRA-Studio
SwiftA native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.
tunelog
Self-hosted music recommendation that learns your taste from skips and replays no ratings needed.
open-edit
TypeScriptOpen-source, agent-driven editing pipeline: create subtitles, motion graphics, slides, edit and render videos.
unsloth
PythonLocal UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.