Chatterbox-Turbo

import torchaudio as ta
from chatterbox.tts_turbo import ChatterboxTurboTTS

# Load the Turbo model
model = ChatterboxTurboTTS.from_pretrained(device="cuda")

# Generate speech
text = "Hello, welcome to Chatterbox Turbo!"
wav = model.generate(text)

ta.save("output.wav", wav, model.sr)

import torchaudio as ta
from chatterbox.tts_turbo import ChatterboxTurboTTS

model = ChatterboxTurboTTS.from_pretrained(device="cuda")

# Generate with paralinguistic tags
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?"

wav = model.generate(text)
ta.save("test-turbo.wav", wav, model.sr)

import torchaudio as ta
from chatterbox.tts_turbo import ChatterboxTurboTTS

model = ChatterboxTurboTTS.from_pretrained(device="cuda")

# Generate with voice cloning
text = "Hi there, Sarah here from MochaFone calling you back [chuckle], have you got one minute to chat about the billing issue?"

# Provide a 5-10 second reference clip
wav = model.generate(text, audio_prompt_path="your_10s_ref_clip.wav")

ta.save("cloned-voice.wav", wav, model.sr)

import perth
import librosa

# Load the watermarked audio
watermarked_audio, sr = librosa.load("output.wav", sr=None)

# Initialize watermarker
watermarker = perth.PerthImplicitWatermarker()

# Extract watermark
watermark = watermarker.get_watermark(watermarked_audio, sample_rate=sr)
print(f"Extracted watermark: {watermark}")  # 0.0 or 1.0