Update app.py

app.py

@@ -3,104 +3,40 @@ 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
-
-
+# Initialize Kokoro components
 def get_style_vector_choices(directory="voices"):
+    if not os.path.exists(directory): return []
     return [file for file in os.listdir(directory) if file.endswith(".pt")]
 
-
 def get_onnx_models(directory="weights"):
+    if not os.path.exists(directory): return []
     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,
-        style_vector: str,
-        output_file_format: str = "wav",
-        speed: float = 1.0
-):
+def local_tts(text: str, model_path: str, style_vector: str, output_file_format: str = "wav", speed: float = 1.0):
     if len(text) > 0:
         try:
             tokenizer = Tokenizer()
             style_vector_path = os.path.join("voices", style_vector)
-            model_path = os.path.join("weights", model_path)
-
-            inference = Kokoro(model_path, style_vector_path, tokenizer=tokenizer, lang='en-us')
+            model_full_path = os.path.join("weights", model_path)
 
+            inference = Kokoro(model_full_path, style_vector_path, tokenizer=tokenizer, lang='en-us')
             audio, sample_rate = inference.generate_audio(text, speed=speed)
 
             with tempfile.NamedTemporaryFile(suffix=f".{output_file_format}", delete=False) as temp_file:
                 sf.write(temp_file.name, audio, sample_rate)
-                temp_file_path = temp_file.name
-
-            return temp_file_path
-
+                return temp_file.name
         except Exception as e:
-            raise gr.Error(f"An error occurred during TTS inference: {str(e)}")
-    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"),
-    ("Thanks", "Thank you for listening to this audio. It was generated by the Kokoro TTS model.", "assets/thanks.wav")
-]
-
-example_texts = [
-    ["Machine learning models rely on large datasets and complex algorithms to identify patterns and make predictions."],
-    ["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!"],
-    ["Thank you for listening to this audio. It was generated by the Kokoro TTS model."]
-]
-
-# Gradio Interface
-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."
-    )
-    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"
-    )
+            print(f"Inference Error: {e}")
+            return None
+    return None
 
-    # Add example texts and audios
-    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)
+# --- FASTAPI SETUP ---
+app = FastAPI(title="Basyx TTS Hub")
 
-demo.launch(server_name="0.0.0.0")
+@app.post("/v1/audio/speech")
+async def api_tts(request: Request):
+    data = await request.json()