Self-host audio.cpp
v0.9.3High-performance C++ audio inference for local AI models
- Stars
- 3 820
- Port
- 8080 (HTTP server and WebUI)
ghcr.io/0xshug0/audio.cppWhat is audio.cpp?
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.
Should you self-host audio.cpp?
audio.cpp scores 65/100 on selfhost.directory (how scoring works) and ranks #25 of 125 in AI. It has 3 820 GitHub stars.
It shipped 9 stable releases in the past year. The latest, v0.9.3, came out on 26 October 2026. New versions land roughly every 6 days.
Setup is advanced: plan for several services and some ongoing maintenance. An official Docker image is available. It is Other-licensed and written mostly in C++.
Its closest alternative on selfhost.directory is ComfyUI (93/100, 143 701 stars). It scores higher overall, so compare the two before you pick. See audio.cpp vs ComfyUI side by side.
Features
- GGUF Model Format
- JSON PipelinesExperimental
- Multi-backend Support
- Music Generation
- Source Separation
- Speech-to-Text (ASR)
- Streaming Inference
- Text-to-Speech (TTS)
- Voice Cloning
- Voice Conversion
audio.cpp README
More in Audio
AudioserveSimple personal server to serve audiofiles files from folders. Intended primarily for audio books, but anything with decent folder structure will do.
aurralOpen-source self-hosted music discovery with personalized recommendations, rotating playlist flows, and library management. Works standalone or with Lidarr.
BeetsOpen-source, self-hosted music library manager: the beet CLI auto-tags your collection from MusicBrainz and can serve a web UI or an MPD-protocol player.
BokeBoxSelf-hosted private AI podcast studio turning videos, links, articles, and meetings into spoken episodes with customizable persona, voice, and MCP/plugin extensibility.
Breeze TTS 2Self-hosted open-weight TTS model with voice cloning, design from descriptions, and voice direction. Streaming REST API and CLI for real-time synthesis on NVIDIA GPUs.
clean-castSelf-hosted Go app converting YouTube playlists/channels to podcast RSS feeds with on-demand audio download and SponsorBlock sponsor removal.
cloudtunesOpen-source, self-hosted web music player that unifies your Dropbox files and YouTube videos, with playlists, Last.fm scrobbling and MusicBrainz metadata.
ConcatAn open-source, self-hosted desktop and mobile video editor pitched as a CapCut replacement, with local Whisper captions, text-to-speech and 4K export.
DeemixOpen-source, self-hosted Deezer music downloader with a web UI, Electron desktop app and CLI, downloading tracks or playlists at 128, 320 or FLAC bitrate via Docker.
DigirecordDigirecord is a simple, self-hosted web app for recording and sharing audio files. It supports direct recording via the browser, file uploads, and optional S3 storage.
discord-soundboard-botSelf-hosted Discord bot for playing custom sounds and recording voice calls, controlled via a web interface with dashboard for managing sounds and server settings.
docker-kokoroOpen-source, self-hosted TTS API with 54 voices, OpenAI-compatible endpoint, streaming, Docker on CPU/GPU.
0 comments