A local text-to-speech tool for Apple Silicon Macs using Qwen3-TTS through the MLX framework. Text-to-speech means turning written text into spoken audio.

Use it to generate spoken audio from text, design a voice from a written description, and perform speech-to-text transcription locally.

It lets you create speech on the Mac without sending text to a cloud service or using an API key. It is intended for Apple Silicon systems rather than Intel Macs or other operating systems.

mlx-tts — Skill for Claude Code and Codex by renky1025

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/renky1025/agent-skills

agentmods

npx agentmods add skills/renky1025/agent-skills/mlx-tts

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/renky1025/agent-skills/mlx-tts/github.svg)](https://agentmods.dev/skills/renky1025/agent-skills/mlx-tts)

Your own site

<a href="https://agentmods.dev/skills/renky1025/agent-skills/mlx-tts"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/mlx-tts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/renky1025/agent-skills/mlx-tts"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/mlx-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,294 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.04294
Opus 5	$0.00018	$0.02147
Sonnet 5	$0.00007	$0.00859
Haiku 4.5	$0.00004	$0.00429

Measured 11d ago against content hash 42bef96253f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

mlx-tts scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$TMPDIR"

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run([

mlx-tts/SKILL.md · 539 lines

How it starts

The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MLX TTS (Qwen3-TTS)

High-quality local text-to-speech synthesis for Apple Silicon Macs using Qwen3-TTS via MLX framework. Optimized for Apple Neural Engine, runs entirely on-device.

Overview

Qwen3-TTS is a 1.7B parameter TTS model optimized for Apple Silicon (M1/M2/M3/M4) using the MLX framework. Features:

Fast inference: Leverages Apple Neural Engine
Prompt-based voice design: Describe the voice you want, no reference audio needed
ASR support: Speech-to-text included
Low memory: 8-bit quantized, runs on 16GB Mac
Local only: No cloud, no API keys, fully private

When to Use

Have an Apple Silicon Mac (M1/M2/M3/M4)
Need high-quality TTS locally
Want to design voices with text prompts (e.g., "a warm female voice, slightly soft")
Need ASR (speech-to-text) capability
Want fast inference with Apple Neural Engine

When NOT to Use

Non-Mac system (Intel Mac or Windows/Linux) → Use other TTS solutions
Need voice cloning from reference audio → Use other tools
Less than 16GB RAM → May work but slower

Environment Setup

One-Command Install

brew install ffmpeg uv && uv tool install --force "mlx-audio" --prerelease=allow

Verify Installation

uv tool list | grep mlx
# Should show: mlx-audio v0.4.2

Model Download

Models auto-download on first run (~2GB total) to ~/.cache/huggingface/hub/:

mlx-community/Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit
mlx-community/Qwen3-ASR-0.6B-bf16

For China users (accelerated download):

Option 1 - HuggingFace mirror:

export HF_ENDPOINT=https://hf-mirror.com

Option 2 - ModelScope (faster):

pip install modelscope

# Download TTS model
modelscope download \
  --model mlx-community/Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit \
  --local_dir ~/.cache/huggingface/hub/Qwen3-TTS

# Download ASR model
modelscope download \
  --model mlx-community/Qwen3-ASR-0.6B-bf16 \
  --local_dir ~/.cache/huggingface/hub/Qwen3-ASR

Usage

Basic TTS

Read the full file on GitHub · 539 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 539 lines · 36 tokens per session scan C 42bef96253f9

Subscribe to this mod's changes

mlx-tts is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 4,294 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media agent agent-skills skill

imagegen-frontend-web

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…

Leonxlnx/taste-skill · 126 tokens

brandkit

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…

Leonxlnx/taste-skill · 89 tokens

mlx-tts