Downloads · 30 days
28
18% of all-time downloads
smdesai/chatterbox-turbo-4bit
chatterbox-turbo-4bit is a text-to-speech model from smdesai. Use it when you need text read aloud. It is set up for mlx-audio. The card lists the license as apache-2.0.
This model was converted to MLX format from ResembleAI/chatterbox-turbo using mlx-audio version 0.2.8. Refer to the original model card for more details on the model.
Downloads · 30 days
28
18% of all-time downloads
All-time downloads
157
Public
Parameters
626M
415 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors415 MB · 99%
How the weights are stored.
U32582M · 93%
From the Hugging Face model README
This model was converted to MLX format from ResembleAI/chatterbox-turbo using mlx-audio version 0.2.8.
Refer to the original model card for more details on the model.
pip install -U mlx-audio
Voice Cloning:
mlx_audio.tts.generate --model mlx-community/chatterbox-turbo-4bit --text "Oh, that's hilarious! [chuckle] Um anyway, we do have a new model in store. It's the SkyNet T-800 series and it's got basically everything. Including AI integration with ChatGPT and all that jazz. Would you like me to get some prices for you?" --ref_audio path_to_file.wav --play
Chatterbox supports expressive event tags that can be inserted directly into your text to add natural vocal expressions:
| Tag | Description |
|---|---|
[clear throat] | Throat clearing sound |
[sigh] | Sighing expression |
[shush] | Shushing sound |
[cough] | Coughing sound |
[groan] | Groaning expression |
[sniff] | Sniffing sound |
[gasp] | Gasping expression |
[chuckle] | Light chuckling |
[laugh] | Laughter |
mlx_audio.tts.generate --model mlx-community/chatterbox-turbo-4bit --text "[sigh] I can't believe it's Monday again. [groan] But hey, [clear throat] let's make the best of it!" --play
Default Voice:
mlx_audio.tts.generate --model mlx-community/chatterbox-turbo-4bit --text "Oh, that's hilarious! [chuckle] Um anyway, we do have a new model in store. It's the SkyNet T-800 series and it's got basically everything. Including AI integration with ChatGPT and all that jazz. Would you like me to get some prices for you?" --play