Agent infrastructure
audio.cpp
0xshug0/audio.cpp
An all-in-one native audio inference engine covering 100+ TTS, ASR, music, and voice models via CLI, server, and WebUI.
Topics
Related projects
whisplay-ai-chatbot532A pocket-sized AI voice chatbot built on Raspberry Pi and the Whisplay HAT, letting users press a button, speak, and hear spoken replies powered by ASR, LLM and TTS, with optional offline models.
stable-diffusion.cpp7.9kA lightweight C/C++ diffusion-model inference engine built on ggml, supporting Stable Diffusion, FLUX, Wan, Qwen Image, and other image and video models on local CPU or GPU backends.
transcribe.cpp2.1kC-based speech-to-text inference library built on GGML supporting more than sixteen model families, designed for efficient streaming and batch transcription workloads.
bigmoeonedge709An inference engine built on stock llama.cpp that runs oversized MoE models on memory-constrained phones by streaming only routed experts from flash without quality loss.
rocketride-server20.1kOpen-source AI development environment for visually building and running LLM pipelines on a high-performance C++ engine inside your IDE apps.
BackgroundMusic19.4kA macOS audio utility that auto-pauses your music when other sound plays, offers per-application volume control and records system audio.