Qwen TTS Skill

Text-to-speech using Qwen3-TTS CustomVoice model, running locally on Apple Silicon via MLX.

Overview

• Model: mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-4bit (4-bit quantized, ~600MB)
• Runtime: MLX (Apple Silicon GPU acceleration)
• Speakers: 9 built-in voices
• Output: WAV audio files
• Auto-cleanup: Files older than 24 hours are removed automatically

First-time Deployment

Prerequisites