qwen-tts

Generate speech from text using the Qwen3-TTS model on Mac MLX hardware.

Updated Aug 23, 2026

Search Tags:#audio #mlx #tts #speech synthesis #voice generation #qwen-tts

Ready to run

npx skills add https://github.com/kazuph/dotfiles --skill qwen-tts

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qwen-tts
Source: https://github.com/kazuph/dotfiles/tree/main/plugins/kazuph-dotfiles/skills/qwen-tts
Command: npx skills add https://github.com/kazuph/dotfiles --skill qwen-tts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mlx-audio, soundfile, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a streamlined way to generate speech from text using the Qwen3-TTS model, optimized for efficiency and quality on Mac MLX hardware.

Core Features & Use Cases

Text-to-Speech Generation: Convert written text into natural-sounding speech with customizable voice characteristics.
Parameter Tuning: Optimize generation speed (RTF) and voice quality using parameters like max_tokens, temperature, and repetition_penalty.
Use Case: Create voiceovers for videos, generate audio for accessibility features, or develop interactive voice response systems.

Quick Start

Use the qwen-tts skill to generate an audio file named 'greeting.wav' from the text 'Hello, world!' with a cheerful female voice.

Frequently Asked Questions about qwen-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate speech from text on Mac MLX hardware?▼

You can generate speech from text on Mac MLX hardware by using the Qwen3-TTS model, which provides efficient text-to-speech synthesis optimized specifically for Apple Silicon architecture.

Can I control voice characteristics like tone and gender during text-to-speech generation?▼

Yes, text-to-speech generation supports customizable voice characteristics through detailed parameter control, allowing you to specify voice instructions and language selection for tailored audio output.

What parameters should I tune to optimize speech synthesis speed and audio quality?▼

To optimize speech synthesis, adjust sampling parameters like temperature, top_k, top_p, repetition_penalty, and max_tokens to balance RTF performance, audio length, and overall voice quality.

Does Qwen3-TTS require mlx-audio and soundfile dependencies to work?▼

Yes, generating speech with Qwen3-TTS requires the mlx-audio and soundfile dependencies to handle the audio processing framework and output file writing on Mac MLX hardware.

Why does my generated audio file cut off before the text finishes?▼

Generated audio may cut off if the max_tokens parameter is set too low; dynamically adjusting this value ensures optimal audio length to fully cover the input text.