Downloads · 30 days
105
13% of all-time downloads
CosyVoice2-0.5B-fp16
mlx-community/CosyVoice2-0.5B-fp16
CosyVoice2-0.5B-fp16 is a text-to-speech model from mlx-community. Use it when you need text read aloud. It is set up for mlx-audio-plus.
This model was converted to MLX format from FunAudioLLM/CosyVoice2-0.5B using mlx-audio-plus version 0.1.2.
All-time downloads
807
Public
Parameters
782M
1.6 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 99%
At a glance
- Task
- Text-to-Speech
- Library
- mlx-audio-plus
- Model type
- cosyvoice2
- Access
- Public
- Created
- Dec 9, 2025
- Updated
- Dec 11, 2025
- SHA
- 1990483d
Base models
Model card
From the Hugging Face model README
mlx-community/CosyVoice2-0.5B-fp16
This model was converted to MLX format from FunAudioLLM/CosyVoice2-0.5B using mlx-audio-plus version 0.1.2.
Usage
pip install -U mlx-audio-plus
Inference Modes
| Mode | Parameters | Description |
|---|---|---|
| Cross-lingual | ref_audio | Zero-shot TTS (default) |
| Zero-shot | ref_audio + ref_text | Better quality with transcription |
| Instruct | ref_audio + instruct_text | Style control (e.g., "speak slowly") |
| Voice Conversion | source_audio + ref_audio | Convert audio to target voice |
Command line
# Cross-lingual (default)
mlx_audio.tts --model mlx-community/CosyVoice2-0.5B-fp16 --text "Hello!" --ref_audio ref.wav
# Zero-shot (with transcription)
mlx_audio.tts --model mlx-community/CosyVoice2-0.5B-fp16 --text "Hello!" --ref_audio ref.wav --ref_text "Transcription of ref audio."
# Instruct (style control)
mlx_audio.tts --model mlx-community/CosyVoice2-0.5B-fp16 --text "Hello!" --ref_audio ref.wav --instruct_text "Speak slowly and calmly"
# Voice Conversion
mlx_audio.tts --model mlx-community/CosyVoice2-0.5B-fp16 --source_audio source.wav --ref_audio ref.wav
Python
from mlx_audio.tts.generate import generate_audio
generate_audio(
text="Hello, this is CosyVoice2 on MLX!",
model="mlx-community/CosyVoice2-0.5B-fp16",
ref_audio="reference.wav",
file_prefix="output",
)
- Task
- Text-to-Speech
- Library
- mlx-audio-plus
- Type
- cosyvoice2
- Languages
- en, zh, ja, ko
- Created
- Dec 9, 2025
- Updated
- Dec 11, 2025