An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
High-Quality Voice Cloning TTS for 600+ Languages
LLM inference in C/C++
DSPy: The framework for programming—not prompting—language models
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Fully automatic censorship removal for language models
Make any agent harness multimodal-native.
real time face swap and one-click video deepfake with only a single image
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
A platform for building proxies to bypass network restrictions.