# audio.cpp

> Self-hosted C++ framework running 100+ audio models locally with CUDA, Vulkan, Metal, CPU backends, built-in WebUI, no Python deps.

- **Category:** AI
- **Licence:** Other
- **Latest version:** v0.9.3
- **Open source:** oss
- **Languages:** C++
- **Platforms:** Docker, Docker Compose, Linux, NixOS, Homebrew, Build from Source
- **Tags:** Streaming, Audio, Vulkan, Cuda, Docker, AI, Stt, Text To Speech, Cpp, Webui, Text To Speech, Speech To Text, Rocm, Music generation, Edge ai, Apple silicon, Voice ai, Ggml, Openai compatible, Voice cloning, Metal, Asr, Amd Gpu, Voice Conversion, Speech To Speech, Diarization, Yue2, Audio Inference, Hip, Vad, Source Separation, Minimax Music3, Speech Analysis

## Description

This C++ inference framework builds on ggml to run modern audio AI models locally without Python. It covers over 110 model families across TTS, STT, voice cloning, conversion, music generation, separation, VAD, diarization, alignment, and codec tasks. You get a CLI, an HTTP server with OpenAI-compatible endpoints, and an embedded WebUI — all from a single binary. It works on Windows, Linux, and macOS using CUDA, AMD ROCm, Vulkan, Metal, or CPU backends. Daily Docker images are on ghcr.io. Licensed Apache-2.0 with no external service dependencies; models load from local GGUF or safetensors files. The server defaults to port 8080 and supports lazy loading, residency limits, and streaming where models allow.

## Links

- [Homepage](https://github.com/0xshug0/audio.cpp)
- [Docker](ghcr.io/0xshug0/audio.cpp)
- [GitHub Repository](https://github.com/0xShug0/audio.cpp)
- [Docker Documentation](https://github.com/0xShug0/audio.cpp/blob/main/docs/docker.md)
- [Server Guide](https://github.com/0xShug0/audio.cpp/blob/main/app/server/README.md)
- [Usage Guide](https://github.com/0xShug0/audio.cpp/blob/main/docs/usage.md)
- [Build Guides](https://github.com/0xShug0/audio.cpp/tree/main/docs/build)
- [Hugging Face Models](https://huggingface.co/audio-cpp/audio.cpp-gguf)
- [ModelScope Models](https://www.modelscope.cn/models/HereIsMark/audio.cpp-gguf)
- [Colab Notebook](https://colab.research.google.com/github/0xShug0/audio.cpp/blob/main/Notebooks/colab_audio_cpp.ipynb)
- [Audio Model Architecture Atlas](https://huggingface.co/spaces/audio-cpp/Audio-Model-Architecture-Atlas)

---
Source: https://selfhost.directory/project/audio-cpp