Downloads · 30 days
11
14% of all-time downloads
chatterbox-fp16
starkdmi/chatterbox-fp16
chatterbox-fp16 is a text-to-speech model from starkdmi. Use it when you need text read aloud. It is set up for mlx. The card lists the license as apache-2.0.
Multilingual Chatterbox TTS weights in MLX format (fp16).
All-time downloads
77
Public
Parameters
678M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- mlx
- License
- apache-2.0
- Model type
- chatterbox
- Access
- Public
- Created
- Jan 1, 2026
- Updated
- Jan 2, 2026
- SHA
- e68aaba8
Model card
From the Hugging Face model README
Chatterbox Multilingual (MLX) - FP16
Multilingual Chatterbox TTS weights in MLX format (fp16).
Files
model.safetensors(1.26 GB)config.jsongrapheme_mtl_merged_expanded_v1.jsonCangjie5_TC.json
Usage (Swift)
generate \
--weights-dir /path/to/weights \
--text "Hello world." \
--lang en \
--ref-wav-path /path/to/reference.wav \
--out-wav /path/to/output.wav
Usage (Python MLX)
from chatterbox.model import Model
model = Model.from_pretrained("/path/to/weights")
Notes:
- S3TokenizerV2 weights are loaded from the HF cache (
mlx-community/S3TokenizerV2) unless included.
- Task
- Text-to-Speech
- Library
- mlx
- Type
- chatterbox
- License
- apache-2.0
- Created
- Jan 1, 2026
- Updated
- Jan 2, 2026