返回技能列表
mlx-stt
由 guoqiao 提供
Apple Apps & Services—暂无评分
你的评分
简介
Speech-To-Text with MLX (Apple Silicon) and GLM-ASR-Nano-2512 locally.
描述
该技能的功能
Runs speech-to-text transcription locally on Apple Silicon using MLX and open-source models. No API key or external server needed. Default model is GLM-ASR-Nano-2512.
Runs entirely on-device with no usage costs or data leaving the machine, unlike cloud STT APIs.
何时使用
- Transcribing recorded meetings or interviews
- Converting voice memos to text
- Captioning locally stored video files
- Transcribing podcast episodes offline
- Turning audio notes into searchable text
示例工作流
输入
User asks: Transcribe my interview recording at ~/Downloads/interview.m4a
智能体
- 1
Receives the audio file path from the user
- 2
Runs mlx-stt.sh with the provided file path
- 3
ffmpeg converts the audio format if needed
- 4
MLX loads the GLM-ASR-Nano-2512 model (downloads on first run)
- 5
Returns transcript printed to stdout
输出
Full text transcript of the audio file
前置要求
- Apple Silicon Mac (M1 or later) with macOS
安装
clawhub install guoqiao/mlx-stt运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。