Downloads · 30 days
12
20% of all-time downloads
maya1-mlx-bf16
0xhb/maya1-mlx-bf16
maya1-mlx-bf16 is a text-to-speech model from 0xhb. Use it when you need text read aloud. It is set up for mlx.
MLX bfloat16 conversion of maya-research/maya1 for text-to-speech on Apple Silicon. Converted using mlx-lm.
All-time downloads
61
Public
Parameters
3.3B
6.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.6 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- mlx
- Model type
- llama
- Access
- Public
- Created
- Mar 15, 2026
- Updated
- Mar 15, 2026
- SHA
- dccd3ac6
Base models
Model card
From the Hugging Face model README
maya1-mlx-bf16
MLX bfloat16 conversion of maya-research/maya1 for text-to-speech on Apple Silicon. Converted using mlx-lm.
Note: This is the full-precision (bfloat16) variant. It offers the highest quality but runs below real-time on most hardware. Consider the 8-bit or 4-bit variants for faster inference.
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)
- Task
- Text-to-Speech
- Library
- mlx
- Type
- llama
- Created
- Mar 15, 2026
- Updated
- Mar 15, 2026