xttsv2

from auralis import TTS, TTSRequest

# Initialize the model
tts = TTS().from_pretrained("AstraMindAI/xtts2-gpt")

# Create a TTS request
request = TTSRequest(
    text="Hello Earth! This is Auralis speaking.",
    speaker_files=["reference.wav"]
)

# Generate speech
output = tts.generate_speech(request)
output.save("output.wav")

def process_book(chapter_file: str, speaker_file: str):
    # Read chapter
    with open(chapter_file, 'r') as f:
        chapter = f.read()
    
    # You can pass the whole book, auralis will take care of splitting
    
    request = TTSRequest(
            text=chapter,
            speaker_files=[speaker_file],
            audio_config=AudioPreprocessingConfig(
                enhance_speech=True,
                normalize=True
            )
        )
        
    output = tts.generate_speech(request)
    
    output.play()
    output.save("chapter_output.wav")

# Example usage
process_book("chapter1.txt", "reference_voice.wav")