Skip to content
TakoAPI
Back to skills

mlx-stt

by guoqiao

Apple Apps & Services
3.0kDownloads reported by clawskills.sh
1Stars
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Speech-To-Text with MLX (Apple Silicon) and GLM-ASR-Nano-2512 locally.

Description

What This Skill Does

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.

When to Use It

  • 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

Example Workflow

INPUT

User asks: Transcribe my interview recording at ~/Downloads/interview.m4a

AGENT
  1. 1

    Receives the audio file path from the user

  2. 2

    Runs mlx-stt.sh with the provided file path

  3. 3

    ffmpeg converts the audio format if needed

  4. 4

    MLX loads the GLM-ASR-Nano-2512 model (downloads on first run)

  5. 5

    Returns transcript printed to stdout

OUTPUT

Full text transcript of the audio file

Requirements

  • Apple Silicon Mac (M1 or later) with macOS

Installation

clawhub install guoqiao/mlx-stt

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links