---
title: Qwen3-TTS Apple Silicon Benchmarks
summary: Qwen3-TTS is Alibaba's speech line. The 12 Hz in every repo name is its audio token rate. GroundSlate installs four checkpoints for two jobs: a Base checkpoint speaks your scripts, and a CustomVoice or VoiceDesign checkpoint makes a voice once and is not used after that.
---

# Qwen3-TTS Apple Silicon Benchmarks

Qwen3-TTS is Alibaba's speech line. The 12 Hz in every repo name is its audio token rate. GroundSlate installs four checkpoints for two jobs: a Base checkpoint speaks your scripts, and a CustomVoice or VoiceDesign checkpoint makes a voice once and is not used after that.

- Maker: Alibaba
- Maker page: /resources/groundslate/benchmarks/makers/alibaba
- Site: https://qwenlm.github.io

## Models

- Qwen3-TTS 1.7B (`mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit`): one line 8.57s, six lines 14.86s. /resources/groundslate/benchmarks/voice/qwen3-tts-1-7b
