---
title: Voice on a Mac
summary: How long GroundSlate's voice model takes to speak on Apple Silicon, through the same synthesize_speech call an AI assistant makes: one line on its own, then six lines in a single call.
---

# Voice on a Mac

How long GroundSlate's voice model takes to speak on Apple Silicon, through the same synthesize_speech call an AI assistant makes: one line on its own, then six lines in a single call.

## Machines

- [MacBook Pro, Apple M3 Max, 64 GB unified memory](/resources/groundslate/benchmarks/machines/macbook-pro-m3-max-64): Reference Mac

## The measurement

- Machine: MacBook Pro, Apple M3 Max, 64 GB unified memory
- Run: 2026-08-28, 2026-08-28-macbook-pro-m3-max-64

## Speech speed, one line against six

- One line: One synthesize_speech call with one line of script, using a voice that already exists.
- Six lines: One synthesize_speech call with six lines.

| Model | Repo | Size | One line | One line realtime | Six lines | Six lines realtime |
| --- | --- | --- | --- | --- | --- | --- |
| Qwen3-TTS 1.7B | `mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit` | 2.3 GB | 8.57s | 0.95× | 14.86s | 1.49× |

## Findings

One line on its own ran at 0.95× realtime, a little slower than the line plays. Six lines in one call ran at 1.49×. GroundSlate speaks one request at a time, so six separate calls wait in line. For anything longer than a sentence, pass the lines together with lines=[...].
GroundSlate keeps every voice it makes. Asking for the same voice again returns the saved one in about a second.
A voice made with the 0.6B model speaks with whichever size the Mac is set to. If that is 1.7B, the audio comes from 1.7B even though the voice itself was made with 0.6B.

## Methodology

- Machine: MacBook Pro, Apple M3 Max, 64 GB unified memory
- Engine: mlx
- Default model: mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit
- Models locked: Yes
- Path: Timed through the synthesize_speech tool, so the figure includes the queue and saving the file to the library.
- Tier: 1.7B, set once for the whole Mac. It peaks at 11.0 GB of memory, against 2.4 GB for 0.6B.
- Voice: Already made and saved. Making a voice is a separate one-time step and is not counted here.

## Models and tools

### Qwen3-TTS 1.7B

- Repo: `mlx-community/Qwen3-TTS-12Hz-1.7B-Base-4bit`
- Maker: Alibaba
- License: [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)
- GroundSlate default
- Size: 2.3 GB
- Tools: synthesize_speech, preview_voice, list_voices, get_voice, attach_voice, voice_status, list_generations
- Page: /resources/groundslate/benchmarks/voice/qwen3-tts-1-7b