ChatterboxTTS

class ChatterboxTTS:
    def __init__(
        self,
        t3: T3,
        s3gen: S3Gen,
        ve: VoiceEncoder,
        tokenizer: EnTokenizer,
        device: str,
        conds: Conditionals = None,
    )

@classmethod
def from_pretrained(cls, device: str) -> 'ChatterboxTTS'

from chatterbox import ChatterboxTTS
import torch

# Load on GPU
device = "cuda" if torch.cuda.is_available() else "cpu"
model = ChatterboxTTS.from_pretrained(device)

@classmethod
def from_local(cls, ckpt_dir: str, device: str) -> 'ChatterboxTTS'

def prepare_conditionals(
    self,
    wav_fpath: str,
    exaggeration: float = 0.5
)

# Prepare voice from reference audio
model.prepare_conditionals(
    wav_fpath="voice_sample.wav",
    exaggeration=0.5
)

def generate(
    self,
    text: str,
    repetition_penalty: float = 1.2,
    min_p: float = 0.05,
    top_p: float = 1.0,
    audio_prompt_path: str = None,
    exaggeration: float = 0.5,
    cfg_weight: float = 0.5,
    temperature: float = 0.8,
) -> torch.Tensor

import torchaudio

# Generate speech with prepared conditionals
audio = model.generate(
    text="Hello, this is a demonstration of Chatterbox TTS.",
    temperature=0.8,
    cfg_weight=0.5,
    exaggeration=0.5,
    repetition_penalty=1.2,
    min_p=0.05
)

# Save to file
torchaudio.save("output.wav", audio, model.sr)

# Or generate with a new voice in one call
audio = model.generate(
    text="Hello world!",
    audio_prompt_path="new_voice.wav",
    exaggeration=0.7
)