Initial clean deploy of Kokoro voice pipeline serverless containerr

app,py

@@ -0,0 +1,44 @@
+import gradio as gr
+import outetts
+import soundfile as sf
+import tempfile
+import os
+
+# Initialize the OuteTTS pipeline (uses 0.1-350M by default)
+model_config = outetts.HFModelConfig_v1(
+    model_path="OuteAI/OuteTTS-0.1-350M",
+    language="en", 
+)
+interface = outetts.InterfaceHF(model_config)
+
+def generate_speech(text: str, speed: float, temperature: float):
+    # Setup generation configuration
+    gen_config = outetts.GenerationConfig(
+        text=text,
+        temperature=temperature,
+        speed=speed
+    )
+    
+    # Generate the audio array
+    output = interface.generate(gen_config)
+    
+    # Save the output buffer array to a temporary WAV file
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".wav")
+    sf.write(temp_file.name, output.audio, output.sr)
+    
+    return temp_file.name
+
+# Create Gradio interface for both UI and API usage
+demo = gr.Interface(
+    fn=generate_speech,
+    inputs=[
+        gr.Textbox(label="Text to Speech", value="Hello, welcome to OuteTTS speech api."),
+        gr.Slider(minimum=0.5, maximum=2.0, value=1.0, step=0.1, label="Speed"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.1, step=0.05, label="Temperature")
+    ],
+    outputs=gr.Audio(label="Generated Audio", type="filepath"),
+    title="OuteTTS API Endpoint"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+outetts==0.2.3
+gradio==4.40.0
+soundfile
+numpy