# Audio.cpp

Audio.cpp is a self-hosted ai app. audio.cpp for Unraid: community-maintained installation templates using unmodified upstream Docker images and the native WebUI/audio API. It is open source and self-hosted, installable on Unraid.

Canonical page: https://ourlocalhost.com/app/2629/audio-cpp

## Description

audio.cpp for Unraid: community-maintained installation templates using unmodified upstream Docker images and the native WebUI/audio API. Choose CPU, NVIDIA CUDA 12, NVIDIA CUDA 13, or AMD/Intel Vulkan (not yet hardware-tested) when installing. No models or personal configuration are bundled. Images follow upstream rolling Docker builds, not exclusively numbered releases. BETA: isolated runtime and private installation tests passed on one host; public branch selection and full deployment acceptance remain pending. See the README for tested images and limitations.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

77/100 (Good), based on 3 of 4 factors.
- Maintained: 100 (last commit 8 days ago)
- Popular: 73 (4,216 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)

## Links

- Unraid: https://ca.unraid.net/apps/audio-cpp-0d9zlgk0zyarso?q=audio-cpp

## Common questions

### Does audio.cpp require Python to run?

No, it is described as an all-in-one pure C++ inference engine for audio models with no Python dependency.

### Can audio.cpp be run with GGUF models through a WebUI and Docker?

Yes, it is described as C++ audio inference with GGUF, WebUI, and Docker.

### Can audio.cpp be used as the STT engine in TranscrIA?

Yes, TranscrIA integrates audio.cpp as a first-class STT engine for a self-hosted meeting transcription platform with diarization and local LLM correction.

### Does audio.cpp support both TTS and STT workloads?

It supports TTS, STT, VAD, voice conversion, and music generation.

---
Source: Our Local Host (https://ourlocalhost.com/app/2629/audio-cpp), the self-hosted and open-source app directory.
