OmniVoice-Studio
Text to Speech
v0.5.7
VoiceStudio is a fully-local voice studio for people who want voice AI without renting it: clone a voice from a short reference recording, invent new voices …2d agoAGPL-3.0DockerModerate
Projects tagged #Cuda
~/index>
--sort
32 projects· by score
Projects
llama.cpp
LLM Inference
v0.8.0llama.cpp is a high-performance LLM inference engine written in plain C/C++ with zero dependencies.todayMITDockerModerate
vLLM
LLM Inference
v0.32.0vLLM is a high-performance library for running large language model inference and serving, created at UC Berkeley's Sky Computing Lab.10d agoApache-2.0DockerModerate
sglang
LLM Inference
v0.5.22SGLang is a high-performance serving framework for large language models, vision-language models, and diffusion models.9d agoApache-2.0DockerAdvanced
ACE-Step
AI
v0.1.8ACE-Step 1.5 is an open-source music foundation model that turns text prompts, lyrics or reference audio into complete songs, aimed at artists, producers and…5mo agoMITNo DockerDemoModerate
Fish Speech
Text to Speech
v1.5.1Fish Speech is Fish Audio's open-weight text-to-speech stack, built around two models that share one command line and one API server: the 35B-A3B Drama 3 fla…14d agoDockerAdvanced
Viseron
Video Surveillance
v3.7.0Viseron is a self-hosted Network Video Recorder and AI Computer Vision application that runs entirely on your own hardware.1mo agoMITDockerDemoModerate
Stable Diffusion WebUI Forge
Image Generation
previousForge is a reworking of AUTOMATIC1111's Stable Diffusion WebUI, built on Gradio, that reorganizes how models live on the graphics card so inference runs fast…7d agoAGPL-3.0No DockerModerate
gpustack
LLM Inference
v2.3.0GPUStack is an open-source (Apache-2.0) manager for GPU clusters, built for serving AI models and handing out on-demand, SSH-accessible GPU instances.5d agoApache-2.0DockerModerate
audio.cpp
AI
v0.9.3This C++ inference framework builds on ggml to run modern audio AI models locally without Python.todayDockerAdvanced
beam
AI
gateway-0.1.837Beta9 is an open-source platform for running serverless AI workloads on your own infrastructure.1d agoAGPL-3.0No DockerAdvanced
aphrodite-engine
LLM Inference
v0.24.1Sonar is a self-hosted serving engine for Hugging Face language and multimodal models, aimed at people who want to host LLMs on hardware they control.1mo agoAGPL-3.0No DockerAdvanced
tabbyAPI
LLM Inference
0.0.1TabbyAPI is a FastAPI-based application that serves as the official API backend for ExllamaV3, enabling self-hosted LLM inference with an OpenAI-compatible API.4mo agoAGPL-3.0DockerAdvanced
GPU-Hot
Monitoring & observability
v1.9.2GPU Hot is a lightweight, web-based dashboard for monitoring NVIDIA GPUs in real time.3mo agoMITDockerDemoEasy
docker-immich
Photo Management
2026.0.0imagegenius/immich packages the Immich photo and video backup application into a monolithic Docker container that includes the server, machine learning infer…4mo agoGPL-3.0DockerModerate
An open-weight text-to-speech system for real-time interaction that leads the Artificial Analysis leaderboard among open models.Breeze TTS 2
AI
15d agoApache-2.0No DockerAdvanced
chatterbox-tts-api
Text to Speech
v1.0.1Chatterbox TTS API is a FastAPI-powered REST server that provides an OpenAI-compatible text-to-speech endpoint with voice cloning capabilities.1y agoAGPL-3.0No DockerDemoModerate
VideoHighlighter
Video
0.14.2VideoHighlighter is a free, open-source desktop application for Windows, macOS, and Linux that performs local AI video analysis.todayAGPL-3.0No DockerModerate
Self-Hosted AI Stack
AI Chat
v2026.10.2Self-Hosted AI Stack is a Docker Compose project that bundles multiple AI services into a single deployable stack.todayMITDockerModerate
ggrun
LLM Inference
v3.2.12ggrun (from "gguf run") is a launcher for running local large language models on your own hardware.todayMITNo DockerModerate
AReno
AI
v0.10.0AReno is a compact toolkit for training and serving large language models using reinforcement learning on a single machine.5d agoApache-2.0DockerAdvanced
ScribeCrate
Transcription
v2026.10.2ScribeCrate is an open-source transcription server you run on your own hardware.todayDockerDemoModerate
ExLlama is a standalone Python, C++ and CUDA take on the Llama architecture aimed at people who want to run 4-bit GPTQ checkpoints on consumer NVIDIA cards.exllama
LLM Inference
3y agoMITNo DockerAdvanced
SNDR Core Engine
LLM Inference
v12.1.0Genesis is a runtime patch layer for vLLM that applies hundreds of small changes at startup, letting large open models run on 24 GB consumer NVIDIA cards.28d agoApache-2.0No DockerAdvanced
Dawn
Developer Tools
v0.102.0Dawn is a compact functional programming language with immutable data structures, algebraic data types, and exhaustive pattern matching.todayApache-2.0No DockerDemoAdvanced
microWakeWord-Trainer-Nvidia-Docker
AI
v47.3microWakeWord Trainer is a self-hosted Docker application for training custom wake word models (microWakeWord, openWakeWord, NanoWakeWord CNN/GRU) using NVID…todayDockerAdvanced
docker-whisper-live
AI
v2026.10.2This self-hosted transcription server handles live microphone audio and streams via WebSocket, delivering progressive text segments.3d agoDockerDemoModerate
docker-kokoro
AI
v2026.10.2A self-hosted text-to-speech service that runs locally on your hardware.3d agoDockerEasy
