kugelaudio-0-open

from kugelaudio_open import (
    KugelAudioForConditionalGenerationInference,
    KugelAudioProcessor,
)
import torch

# Load model
device = "cuda" if torch.cuda.is_available() else "cpu"
model = KugelAudioForConditionalGenerationInference.from_pretrained(
    "kugelaudio/kugelaudio-0-open",
    torch_dtype=torch.bfloat16,
).to(device)
model.eval()

processor = KugelAudioProcessor.from_pretrained("kugelaudio/kugelaudio-0-open")

# Strip encoder weights to save VRAM (only decoders needed for inference)
model.model.strip_encoders()

# See available voices
print(processor.get_available_voices())  # ["default", "warm", "clear"]

# Generate speech with a specific voice
inputs = processor(text="Hallo Welt! Das ist KugelAudio.", voice="default", return_tensors="pt")
inputs = {k: v.to(device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}

with torch.no_grad():
    outputs = model.generate(**inputs, cfg_scale=3.0)

# Save audio
processor.save_audio(outputs.speech_outputs[0], "output.wav")

# List available voices
voices = processor.get_available_voices()
print(voices)  # ["default", "warm", "clear"]

# Generate with a specific voice
inputs = processor(text="Hallo, das ist eine warme Stimme!", voice="warm", return_tensors="pt")
inputs = {k: v.to(device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}

with torch.no_grad():
    outputs = model.generate(**inputs, cfg_scale=3.0)

processor.save_audio(outputs.speech_outputs[0], "warm_voice_output.wav")