Chatterbox-Multilingual

import torchaudio as ta
from chatterbox.mtl_tts import ChatterboxMultilingualTTS

# Load the multilingual model
model = ChatterboxMultilingualTTS.from_pretrained(device="cuda")

# Generate French speech
french_text = "Bonjour, comment ça va? Ceci est le modèle de synthèse vocale multilingue Chatterbox, il prend en charge 23 langues."
wav = model.generate(french_text, language_id="fr")

ta.save("test-french.wav", wav, model.sr)

import torchaudio as ta
from chatterbox.mtl_tts import ChatterboxMultilingualTTS

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

# Spanish
spanish_text = "Hola, ¿cómo estás? Este es un ejemplo de síntesis de voz en español."
wav_spanish = model.generate(spanish_text, language_id="es")
ta.save("test-spanish.wav", wav_spanish, model.sr)

# Chinese
chinese_text = "你好，今天天气真不错，希望你有一个愉快的周末。"
wav_chinese = model.generate(chinese_text, language_id="zh")
ta.save("test-chinese.wav", wav_chinese, model.sr)

# German
german_text = "Guten Tag, wie geht es Ihnen? Dies ist ein Test der deutschen Sprachsynthese."
wav_german = model.generate(german_text, language_id="de")
ta.save("test-german.wav", wav_german, model.sr)

import torchaudio as ta
from chatterbox.mtl_tts import ChatterboxMultilingualTTS

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

# Clone a voice and use it for different languages
reference_audio = "english_speaker.wav"

# Generate in French with English speaker's voice
french_text = "Bonjour, je parle français maintenant."
wav = model.generate(
    french_text,
    language_id="fr",
    audio_prompt_path=reference_audio
)

ta.save("french-with-english-voice.wav", wav, model.sr)

from chatterbox.mtl_tts import ChatterboxMultilingualTTS

# Get dictionary of all supported languages
languages = ChatterboxMultilingualTTS.get_supported_languages()

for code, name in languages.items():
    print(f"{code}: {name}")

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