0xShug0/audio.cpp

Health v2 · maintenance only

Flags: young no_license

Adoption not part of the score

2022 stars · 243 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

audio.cpp is a pure C++ inference engine for audio models built on ggml, supporting TTS, STT, VAD, voice conversion, music generation, and more without any Python dependency. It runs on Windows, Linux, and macOS with CUDA, AMD, Apple Silicon, and CPU backends, offering significant performance gains over Python reference implementations.

Use cases

• run text-to-speech locally without python
• transcribe audio to text offline in c++
• clone a voice from a short sample
• do voice activity detection on a stream
• convert one voice to another
• generate music or audio from a model locally
• diarize speakers in meeting recordings
• separate audio sources like vocals and background

When to choose

• you want fast local audio model inference without python or conda dependency hell
• you need a portable native runtime across windows, linux, and macos with gpu support
• you need production-grade tts or asr with lower latency than python reference paths
• you want gguf quantized models to reduce vram usage

When to avoid

• you need a model family not yet supported by the engine
• you prefer python tooling and ecosystem integration
• you need a stable long-term api since the project is young and rapidly evolving

Facets

library · maturity active

llm-inference tts speech-recognition audio-processing machine-learning speech-processing machine-learning artificial-intelligence cpp cross-platform cli ggml tts asr voice-cloning vad voice-conversion source-separation gguf local-inference no-python audio gpu docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="0xShug0/audio.cpp")