Saltar al contenido
TakoAPI
Volver a skills

mlx-audio-server

por guoqiao

Media & Streaming
2.2kDescargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

A fast, accurate, and fully local OpenAI-compatible API.

Descripción

Qué hace esta skill

Runs an OpenAI-compatible STT and TTS API server locally on Apple Silicon Macs using the MLX framework. Installs and manages itself as a persistent LaunchAgent via Homebrew. Accepts audio or video files for transcription and text strings for speech synthesis.

Runs fully offline on Apple Silicon with an OpenAI-compatible API, so existing tools that target OpenAI audio endpoints work without code changes or data leaving the machine.

Cuándo usarla

  • Transcribing local meeting recordings without sending audio to the cloud
  • Generating spoken audio from text in automation pipelines
  • Replacing OpenAI Whisper/TTS API calls with a local drop-in endpoint
  • Converting video files to text transcripts on a Mac
  • Running always-on voice processing for offline or privacy-sensitive workflows

Flujo de trabajo de ejemplo

ENTRADA

User asks: transcribe this interview recording at ./interview.mp4

AGENTE
  1. 1

    Calls run_stt.sh with the video path

  2. 2

    ffmpeg converts the file to wav internally

  3. 3

    Server sends audio to local mlx-community/glm-asr-nano-2512-8bit model

  4. 4

    Transcript text is returned to stdout

SALIDA

Plain text transcript of the interview

Requisitos

  • Apple Silicon Mac (M1 or later)
  • Homebrew installed

Instalación

clawhub install guoqiao/mlx-audio-server

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

Enlaces