Update app.py

app.py

@@ -1,23 +1,20 @@
-
 import os
 import gradio as gr
 import tempfile
 import soundfile as sf
 from models import Tokenizer, Kokoro
+from fastapi import FastAPI, Request
+from fastapi.responses import FileResponse
+import uvicorn
 
-# Function to fetch available style vectors dynamically
-
+# --- EXISTING LOGIC (UNCHANGED) ---
 
 def get_style_vector_choices(directory="voices"):
     return [file for file in os.listdir(directory) if file.endswith(".pt")]
 
-
 def get_onnx_models(directory="weights"):
     return [file for file in os.listdir(directory) if file.endswith(".onnx")]
 
-# Function to perform TTS using your local model
-
-
 def local_tts(
         text: str,
         model_path: str,
@@ -29,9 +26,9 @@ def local_tts(
         try:
             tokenizer = Tokenizer()
             style_vector_path = os.path.join("voices", style_vector)
-            model_path = os.path.join("weights", model_path)
+            model_path_full = os.path.join("weights", model_path)
 
-            inference = Kokoro(model_path, style_vector_path, tokenizer=tokenizer, lang='en-us')
+            inference = Kokoro(model_path_full, style_vector_path, tokenizer=tokenizer, lang='en-us')
 
             audio, sample_rate = inference.generate_audio(text, speed=speed)
 
@@ -46,12 +43,9 @@ def local_tts(
     else:
         raise gr.Error("Input text cannot be empty.")
 
-
-# Get the list of available style vectors
 style_vector_choices = get_style_vector_choices()
 onnx_models_choices = get_onnx_models()
 
-# sample texts and their corresponding audio
 sample_outputs = [
     ("Educational Note", "Machine learning models rely on large datasets and complex algorithms to identify patterns and make predictions.", "assets/edu_note.wav"),
     ("Fun Fact", "Did you know that honey never spoils? Archaeologists have found pots of honey in ancient Egyptian tombs that are over 3,000 years old and still edible!", "assets/fun_fact.wav"),
@@ -64,45 +58,51 @@ example_texts = [
     ["Thank you for listening to this audio. It was generated by the Kokoro TTS model."]
 ]
 
-# Gradio Interface
+# --- GRADIO INTERFACE (UNCHANGED) ---
+
 with gr.Blocks() as demo:
     gr.Markdown("## <center> Kokoro TTS ONNX Inference | [GitHub Link](https://github.com/yakhyo/kokoro-onnx) </center>")
-
-    # Model-specific inputs
     with gr.Row(variant="panel"):
         model_path = gr.Dropdown(choices=onnx_models_choices, label="ONNX Model Path", value=onnx_models_choices[0])
         style_vector = gr.Dropdown(choices=style_vector_choices, label="Style Vector", value=style_vector_choices[0])
         output_file_format = gr.Dropdown(choices=["wav", "mp3"], label="Output Format", value="wav")
         speed = gr.Slider(minimum=0.5, maximum=2.0, value=1.0, step=0.1, label="Speed")
 
-    # Text input and output
-    text = gr.Textbox(
-        label="Input Text",
-        placeholder="Enter text to convert to speech."
-    )
+    text = gr.Textbox(label="Input Text", placeholder="Enter text to convert to speech.")
     btn = gr.Button("Generate Speech")
     output_audio = gr.Audio(label="Generated Audio", type="filepath")
 
-    # Link inputs and outputs
-    btn.click(
-        fn=local_tts,
-        inputs=[text, model_path, style_vector, output_file_format, speed],
-        outputs=output_audio
-    )
-
-    # Add example texts
-    gr.Examples(
-        examples=example_texts,
-        inputs=[text],
-        label="Click an example to populate the input text"
-    )
-
-    # Add example texts and audios
+    btn.click(fn=local_tts, inputs=[text, model_path, style_vector, output_file_format, speed], outputs=output_audio)
+
+    gr.Examples(examples=example_texts, inputs=[text], label="Click an example to populate the input text")
     gr.Markdown("### Sample Texts and Audio")
     for topic, sample_text, sample_audio in sample_outputs:
         with gr.Row():
             gr.Textbox(value=sample_text, label=topic, interactive=False)
             gr.Audio(value=sample_audio, label="Example Audio", type="filepath", interactive=False)
 
-demo.launch(server_name="0.0.0.0")
-
+# --- FASTAPI WRAPPER & STARTUP ---
+
+app = FastAPI()
+
+@app.post("/v1/audio/speech")
+async def api_speech(request: Request):
+    """
+    OpenAI-compatible /v1/audio/speech endpoint for automation.
+    Expects JSON: {"input": "text", "voice": "voice_file.pt", "model": "model_file.onnx"}
+    """
+    data = await request.json()
+    input_text = data.get("input", "")
+    m_path = data.get("model", onnx_models_choices[0])
+    s_vec = data.get("voice", style_vector_choices[0])
+    spd = float(data.get("speed", 1.0))
+    
+    file_path = local_tts(input_text, m_path, s_vec, speed=spd)
+    return FileResponse(file_path, media_type="audio/wav")
+
+# Mount Gradio into the FastAPI app
+app = gr.mount_gradio_app(app, demo, path="/")
+
+if __name__ == "__main__":
+    # Runs on port 7860 as expected by the Dockerfile/Hugging Face
+    uvicorn.run(app, host="0.0.0.0", port=7860)