ramimu/chatterbox-voice-cloning-model

Chatterbox Voice Cloning Model Files

This repository contains the model files for the Chatterbox Voice Cloning application.

Model Files

• s3gen.pt - Speech synthesis generator model
• t3_cfg.pt - Text-to-speech configuration model
• ve.pt - Voice encoder model
• tokenizer.json - Text tokenizer configuration

Usage

These files are automatically downloaded by the Chatterbox Voice Cloning Space when it starts up.

You can also use them programmatically:

from huggingface_hub import hf_hub_download

# Download a specific model file
model_path = hf_hub_download(
    repo_id="ramimu/chatterbox-voice-cloning-model",
    filename="s3gen.pt"
)

Model Information

• Library: ChatterboxTTS
• Task: Voice Cloning / Text-to-Speech
• Format: PyTorch (.pt files)
• Size: ~3GB total