MLX STT

在 macOS Apple Silicon 上通过 MLX 与开源模型（默认 GLM-ASR-Nano-2512）本地完成语音转文字：install.sh 用 brew 安装 ffmpeg、uv、mlx_audio，mlx-stt.sh 接收音频文件路径并把转录结果打印到 stdout。无需 API key 和服务器，首次运行需下载模型。

guoqiao

热度 95.16

最近更新 2026-05-11 15:52:12

分类：效率依赖：代码执行 / 读写文件应用场景：文件转换 / 自动化脚本

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add mlx-stt

Metadata

name: mlx-stt
description: Speech-To-Text with MLX (Apple Silicon) and opensource models (default GLM-ASR-Nano-2512) locally.
version: 1.0.7
author: guoqiao
metadata: {"openclaw":{"always":true,"emoji":"🦞","homepage":"https://github.com/guoqiao/skills/blob/main/mlx-stt/mlx-stt/SKILL.md","os":["darwin"],"requires":{"bins":["brew"]}}}
triggers: ["/mlx-stt <audio>","STT ...","ASR ...","Transcribe ...","Convert audio to text ..."]

MLX STT

Speech-To-Text/ASR/Transcribe with MLX (Apple Silicon) and opensource models (default GLM-ASR-Nano-2512) locally.

Free and Accurate. No api key required. No server required.

Requirements

mlx: macOS with Apple Silicon
brew: used to install deps if not available

Installation

bash ${baseDir}/install.sh

This script will use brew to install these cli tools if not available:

ffmpeg: convert audio format when needed
uv: install python package and run python script
mlx_audio: do the real job

Usage

To transcribe an audio file, run this script:

bash  ${baseDir}/mlx-stt.sh <audio_file_path>

First run could be a little slow, since it will need to download model.
The transcript result will be printed to stdout.