Saltar al contenido
TakoAPI
Volver a skills

mlx-stt

por guoqiao

Apple Apps & Services
3.0kDescargas según clawskills.sh
1Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

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

Descripción

Qué hace esta skill

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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

Full text transcript of the audio file

Requisitos

  • Apple Silicon Mac (M1 or later) with macOS

Instalación

clawhub install guoqiao/mlx-stt

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces