Aller au contenu
TakoAPI
Retour aux skills

mlx-audio-server

par guoqiao

Media & Streaming
2.2kTéléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

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

Description

Ce que fait ce 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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

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

AGENT
  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

SORTIE

Plain text transcript of the interview

Prérequis

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

Installation

clawhub install guoqiao/mlx-audio-server

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens