Update app.py

app.py

@@ -31,15 +31,15 @@ def gradio_generate(prompt, steps, guidance,duration=10):
     
     
     #wavio.write(output_filename, output_wave, rate=44100, sampwidth=2)
-    unique_filename = f"output_{uuid.uuid4().hex}.wav"
-    print(f"Saving audio to file: {unique_filename}")
+    filename = 'temp.wav'
+    #print(f"Saving audio to file: {unique_filename}")
 
     # Save to file
-    torchaudio.save(unique_filename, output, 44100)
+    torchaudio.save(filename, output, 44100)
     print(f"Audio saved: {unique_filename}")
 
     # Return the path to the generated audio file
-    return unique_filename
+    return filename
 
     #if (output_format == "mp3"):
      #   AudioSegment.from_wav("temp.wav").export("temp.mp3", format = "mp3")
@@ -61,26 +61,47 @@ denoising_steps = gr.Slider(minimum=10, maximum=100, value=25, step=5, label="St
 guidance_scale = gr.Slider(minimum=1, maximum=10, value=4.5, step=0.5, label="Guidance Scale", interactive=True)
 duration_scale = gr.Slider(minimum=1, maximum=30, value=10, step=1, label="Duration", interactive=True)
 
-interface = gr.Interface(
+
+# Gradio interface
+gr_interface = gr.Interface(
     fn=gradio_generate,
-    inputs=[
-        gr.Textbox(label="Prompt", placeholder="Enter your text prompt here"),
-        gr.Slider(0, 30, value=10, label="Duration in Seconds"),
-        gr.Slider(10, 150, value=50, step=5, label="Number of Diffusion Steps"),
-        gr.Slider(1, 10, value=4.5, step=0.5, label="CFG Scale")
-    ],
-    outputs=gr.Audio(type="filepath", label="Generated Audio"),
-    title="TangoFlux Generator",
-    description="Generate variable-length stereo audio at 44.1kHz from text prompts using TangoFlux.",
+    inputs=[input_text, denoising_steps, guidance_scale,duration_scale],
+    outputs=output_audio,
+    title="TangoFlux: ",
+    description=description_text,
+    allow_flagging=False,
+
+
+
+
     examples=[
-    [
-        "Create a serene soundscape of a quiet beach at sunset.",  # Text prompt
- 
-        15,  # Duration in Seconds
-        50,  # Number of Diffusion Steps
-        4.5,  # CFG Scale
-    ]
-    
-])
+        ["Quiet speech and then and airplane flying away"],
+        ["A bicycle peddling on dirt and gravel followed by a man speaking then laughing"],
+        ["Ducks quack and water splashes with some animal screeching in the background"],
+        ["Describe the sound of the ocean"],
+        ["A woman and a baby are having a conversation"],
+        ["A man speaks followed by a popping noise and laughter"],
+        ["A cup is filled from a faucet"],
+        ["An audience cheering and clapping"],
+        ["Rolling thunder with lightning strikes"],
+        ["A dog barking and a cat mewing and a racing car passes by"],
+        ["Gentle water stream, birds chirping and sudden gun shot"],
+        ["A man talking followed by a goat baaing then a metal gate sliding shut as ducks quack and wind blows into a microphone."],
+        ["A dog barking"],
+        ["A cat meowing"],
+        ["Wooden table tapping sound while water pouring"],
+        ["Applause from a crowd with distant clicking and a man speaking over a loudspeaker"],
+        ["two gunshots followed by birds flying away while chirping"],
+        ["Whistling with birds chirping"],
+        ["A person snoring"],
+        ["Motor vehicles are driving with loud engines and a person whistles"],
+        ["People cheering in a stadium while thunder and lightning strikes"],
+        ["A helicopter is in flight"],
+        ["A dog barking and a man talking and a racing car passes by"],
+    ],
+    cache_examples="lazy", # Turn on to cache.
+)
+
+
 
-interface.launch()
+gr_interface.queue(15).launch()