app.py

import gradio as gr
import torch
import torchaudio
from einops import rearrange
from stable_audio_tools import get_pretrained_model
from stable_audio_tools.inference.generation import generate_diffusion_cond

def gen_music(description):
    device = "cuda" if torch.cuda.is_available() else "cpu"
    
    st.title("Generate Music with Stability Audio!!")
    
    # Download model
    model, model_config = get_pretrained_model("stabilityai/stable-audio-open-1.0")
    sample_rate = model_config["sample_rate"]
    sample_size = model_config["sample_size"]
    
    model = model.to(device)
    
    # Set up text and timing conditioning
    conditioning = [{
    	"prompt": f"{description.placeholder}",
    }]
    
    # Generate stereo audio
    output = generate_diffusion_cond(
    	model,
    	conditioning=conditioning,
    	sample_size=sample_size,
    	device=device
    )
    
    # Rearrange audio batch to a single sequence
    output = rearrange(output, "b d n -> d (b n)")
    
    # Peak normalize, clip, convert to int16, and save to file
    output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu()
    torchaudio.save("output.wav", output, sample_rate)

    return "output.wav"


# Define a interface Gradio
description = gr.Textbox(label="Description", placeholder="128 BPM tech house drum loop")
output_path = gr.Audio(label="Generated Music", type="filepath")

gr.Interface(
    fn=gen_music,
    inputs=[description],
    outputs=output_path,
    title="StableAudio Music Generation Demo",
).launch()