- name
- mlx-audio-server
- description
- Local 24x7 OpenAI-compatible API server for STT/TTS, powered by MLX on your Mac.
- metadata
- {"openclaw":{"always":true,"emoji":"🦞","homepage":"https://github.com/guoqiao/skills/blob/main/mlx-audio-server/mlx-audio-server/SKILL.md","os":["darwin"],"requires":{"bins":["brew"]}}}
MLX Audio Server
Local 24x7 OpenAI-compatible API server for STT/TTS, powered by MLX on your Mac.
mlx-audio: The best audio processing library built on Apple's MLX framework, providing fast and efficient text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS) on Apple Silicon.
guoqiao/tap/mlx-audio-server: Homebrew Formula to install mlx-audio with brew, and run mlx_audio.server as a LaunchAgent service on macOS.
Requirements
mlx: macOS with Apple Siliconbrew: used to install deps if not available
Installation
bash ${baseDir}/install.shThis script will:
- install ffmpeg/jq with brew if missing.
- install homebrew formula
mlx-audio-serverfromguoqiao/tap - start brew service for
mlx-audio-server
Usage
STT/Speech-To-Text(default model: mlx-community/glm-asr-nano-2512-8bit):
# input will be converted to wav with ffmpeg, if not yet.
# output will be transcript text only.
bash ${baseDir}/run_stt.sh <audio_or_video_path>TTS/Text-To-Speech(default model: mlx-community/Qwen3-TTS-12Hz-1.7B-VoiceDesign-bf16):
# audio will be saved into a tmp dir, with default name `speech.wav`, and print to stdout.
bash ${baseDir}/run_tts.sh "Hello, Human!"
# or you can specify a output dir
bash ${baseDir}/run_tts.sh "Hello, Human!" ./output
# output will be audio path only.You can use both scripts directly, or as example/reference.