maya1-mlx-8bit

MLX 8-bit quantized conversion of maya-research/maya1 for text-to-speech on Apple Silicon. Converted using mlx-lm.

Recommended variant. Best balance of quality and speed — near real-time on M4 Max. See also: bf16 (highest quality) and 4-bit (fastest).

Benchmarks (M4 Max, 36GB)

Variant	Size	Tokens/s	Real-time factor
bf16	6.2 GB	~51 tok/s	0.50x
8-bit	3.3 GB	~91 tok/s	0.82x
4-bit	1.8 GB	~108 tok/s	1.58x

Quick Start

Requires macOS with Apple Silicon and uv.

# From a text file
uv run tts.py input.txt -o output.wav

# From stdin
echo "Hello world" | uv run tts.py - -o hello.wav

# With a custom voice description
uv run tts.py input.txt -o output.wav -d "Deep male voice, British accent, slow pacing."

CLI Options

Option	Default	Description
input	(required)	Input text file path, or - for stdin
-o, --output	output.wav	Output WAV file path
-d, --description	Calm/clear female voice	Voice description prompt
-m, --model	.	Path to MLX model directory
--max-chars	200	Max characters per chunk
--max-tokens	2048	Max tokens per chunk
--temperature	0.4	Sampling temperature
--top-p	0.9	Top-p sampling
--repetition-penalty	1.1	Repetition penalty

Requirements

• macOS with Apple Silicon (M1 or later)
• uv (dependencies are declared inline via PEP 723)