app.py

import gradio as gr
from transformers import AutoProcessor, BarkModel
import scipy
from IPython.display import Audio

# Load the processor and model
processor = AutoProcessor.from_pretrained("suno/bark")
model = BarkModel.from_pretrained("suno/bark")

def generate_audio(text):
    # Your preset may vary
    voice_preset = "v2/en_speaker_6"
    inputs = processor(text, voice_preset=voice_preset)
    audio_array = model.generate(**inputs)
    audio_array = audio_array.cpu().numpy().squeeze()
    sample_rate = model.generation_config.sample_rate
    
    # Write the output to a .wav file
    scipy.io.wavfile.write("bark_out.wav", rate=sample_rate, data=audio_array)
    return "bark_out.wav"

# Create the Gradio interface
iface = gr.Interface(
    fn=generate_audio,
    inputs=gr.inputs.Textbox(label="标入prompt(input)"),
    outputs=gr.outputs.Audio(label="生成音频(button)", type="file"),
    allow_flagging="never"
)

# Launch the interface
iface.launch()